chore: update vendor submodules to latest upstream

2026-06-16 11:23:19 +00:00 · 2026-05-31 12:37:39 +00:00
740 changed files with 28400 additions and 73926 deletions
@@ -1,119 +0,0 @@
-{
-  "id": "aether-arena-aa",
-  "name": "AetherArena (AA) — Official Spatial-Intelligence Benchmark",
-  "adr": "ADR-149",
-  "adrPath": "docs/adr/ADR-149-public-community-leaderboard-huggingface.md",
-  "status": "Accepted",
-  "initializedDate": "2026-05-30",
-  "targetDate": "2026-08-31",
-  "exitCriteria": "Benchmark INFRASTRUCTURE done, tested, CI-gated, deploy-ready: aa_score_runner.rs passes deterministic fixture test; CI harness-gate green on every PR; aether-arena repo scaffold committed (README four-part framing + aa-submission.toml schema + VERIFY.md); public smoke split committed; HF Space lifecycle skeleton deployed; signed Parquet ledger functional; RuView baseline PCK@20 ~2.5% entered; ADR-149 §7 acceptance test (five-step stranger test) passes. NOTE: ML SOTA (MM-Fi PCK@20 ~72%) is a separate long-running stretch goal blocked on ADR-079 camera-ground-truth — it is NOT an infra exit criterion.",
-  "baselineState": {
-    "adrStatus": "Accepted, committed 2026-05-30",
-    "scorerCode": "ruview_metrics.rs + ablation.rs + proof.rs exist in wifi-densepose-train; aa_score_runner.rs not yet created",
-    "aetherArenaRepo": "does not exist yet — needs user authorization to create ruvnet/aether-arena public repo",
-    "hfSpace": "does not exist yet — needs HF_TOKEN and user authorization to deploy ruvnet/aether-arena HF Space",
-    "smokeDataset": "not committed",
-    "resultsLedger": "not created",
-    "ruviewBaseline": "PCK@20 ~2.5% self-reported, not formally entered",
-    "ciGate": "not added to workflow"
-  },
-  "milestones": {
-    "m1": {
-      "name": "ADR-149 Accepted + committed",
-      "status": "DONE",
-      "completedDate": "2026-05-30",
-      "completionCriteria": "ADR-149 file committed to docs/adr/ with status Accepted",
-      "notes": "Done this session. File at docs/adr/ADR-149-public-community-leaderboard-huggingface.md"
-    },
-    "m2": {
-      "name": "Deterministic scorer runner bin (aa_score_runner.rs)",
-      "status": "NOT_STARTED",
-      "completionCriteria": "aa_score_runner.rs compiles, runs ruview_metrics on a committed fixture, emits RuViewTier + SHA-256 proof hash, mirrors existing *_proof_runner.rs pattern; cargo test passes",
-      "estimatedEffort": "3-5 days",
-      "owner": "wifi-densepose-train crate or new aa-scorer crate"
-    },
-    "m3": {
-      "name": "CI harness-gate: GitHub Actions workflow",
-      "status": "NOT_STARTED",
-      "completionCriteria": "A GitHub Actions workflow runs aa_score_runner on every PR as a build gate; PR fails if scorer fails determinism check; workflow committed and green",
-      "estimatedEffort": "2-3 days",
-      "dependency": "M2 must be done first"
-    },
-    "m4": {
-      "name": "aether-arena repo scaffold",
-      "status": "NOT_STARTED",
-      "completionCriteria": "ruvnet/aether-arena repo created with: README (four-part framing: Public leaderboard / Private eval split / Open scorer / Signed results); aa-submission.toml manifest schema; VERIFY.md (ADR-149 §7 stranger acceptance test); neutrality/governance section (§2.8); contribution guide",
-      "estimatedEffort": "3-5 days",
-      "blockers": ["Needs user authorization to create public ruvnet/aether-arena repo on GitHub"]
-    },
-    "m5": {
-      "name": "Public smoke split committed + private MM-Fi held-out split prep",
-      "status": "NOT_STARTED",
-      "completionCriteria": "Public smoke split committed to aether-arena repo (stranger can score locally); private MM-Fi held-out split prepared under non-public path with CC BY-NC 4.0 attribution; Wi-Pose explicitly excluded from v0",
-      "estimatedEffort": "5-7 days",
-      "riskNotes": "MM-Fi CC BY-NC 4.0: AA must remain non-commercial and carry MM-Fi attribution; raw frames stay in private split; only derived CSI features + scores may be exposed"
-    },
-    "m6": {
-      "name": "HF Space (Gradio) skeleton",
-      "status": "BLOCKED",
-      "completionCriteria": "HF Space deployed at ruvnet/aether-arena with submission lifecycle (submitted->validated->quarantined->smoke_scored->full_scored->published/rejected); sandboxed scorer container wired; basic leaderboard table rendered",
-      "estimatedEffort": "7-10 days",
-      "blockers": [
-        "Needs HF_TOKEN — check .env for HF_TOKEN or HUGGINGFACE_TOKEN",
-        "Needs user authorization to create/deploy ruvnet/aether-arena HF Space (outward-facing public deployment)"
-      ]
-    },
-    "m7": {
-      "name": "Signed append-only Parquet results ledger",
-      "status": "NOT_STARTED",
-      "completionCriteria": "HF dataset ruvnet/aether-arena-results created; append-only Parquet ledger with signed rows; determinism_gate enforced; no row can be silently edited",
-      "estimatedEffort": "3-5 days",
-      "ledgerSchema": "submitter, model_ref, category, feature_set, tier, pck20, oks, mota, vitals_bpm_err, latency_p50, latency_p95, privacy_leakage, cross_room_deg, proof_sha256, scored_at, harness_version",
-      "dependency": "M6 must be scaffolded first"
-    },
-    "m8": {
-      "name": "RuView baseline entry + public launch",
-      "status": "NOT_STARTED",
-      "completionCriteria": "RuView wifi-densepose-pretrained baseline entered (honest PCK@20 ~2.5%); ADR-149 §7 five-step stranger acceptance test passes; v0 live with Presence + Pose + Edge-latency + Determinism categories active; Privacy and Cross-room shown as gated/coming-soon",
-      "estimatedEffort": "3-5 days",
-      "dependency": "M4+M5+M6+M7 complete",
-      "notes": "ML SOTA improvement (PCK@20 ~72%) is a SEPARATE stretch goal blocked on ADR-079 P7-P9 camera ground truth. NOT a blocker for infra launch."
-    }
-  },
-  "activeMilestone": "m2",
-  "completedMilestones": ["m1"],
-  "knownRisks": [
-    "HF_TOKEN not confirmed present in .env — check before M6 work begins",
-    "ruvnet/aether-arena public repo creation is outward-facing — needs explicit user authorization",
-    "MM-Fi CC BY-NC 4.0: AA must stay legally non-commercial and brand-distinct from commercial RuView product; or seek MM-Fi commercial grant before any paid tier",
-    "Wi-Pose has research-use-only terms (no redistribution grant) — excluded from v0; revisit only if terms are clarified with authors",
-    "HF Space free CPU tier may be too slow for Candle/tch inference pipeline — may need ZeroGPU or self-hosted scorer on cognitum-20260110 GCloud A100/L4",
-    "ADR-079 camera-ground-truth (PCK@20 SOTA) is P7-P9 pending — NOT an infra blocker; must not be conflated with AA infra completion",
-    "Neutrality/governance risk: RuView seeded the scorer — must be demonstrably scored through the same public pipeline as any other entrant (§2.8 controls)"
-  ],
-  "driftSignals": {
-    "timeline": "GREEN — just initialized, no timeline pressure yet",
-    "scope": "GREEN — scope locked at four-part structure per ADR-149 §2 decision",
-    "approach": "GREEN — reuse pattern (existing ruview_metrics + proof.rs) confirmed in ADR-149",
-    "dependency": "YELLOW — HF_TOKEN and ruvnet/aether-arena repo authorization are external blockers with unknown ETA",
-    "priority": "GREEN — active feature branch feat/adr-136-146-streaming-engine in progress; AA infra can proceed in parallel on its own branch"
-  },
-  "stretchGoals": {
-    "sotaML": "MM-Fi PCK@20 SOTA ~72% — separate ML effort blocked on ADR-079 P7-P9 camera-ground-truth data collection; NOT an infra exit criterion",
-    "privacyAxis": "ADR-145 §10 membership-inference attacker — activate Privacy leaderboard axis once attacker is implemented and published",
-    "crossRoom": "Multi-room held-out split — activate Cross-room generalization axis",
-    "multiOrgSteering": "Invite co-maintainers from other projects once >=N external entries land"
-  },
-  "sessionHistory": [
-    {
-      "date": "2026-05-30",
-      "type": "initialization",
-      "accomplished": [
-        "ADR-149 Accepted and committed to docs/adr/",
-        "Horizon record initialized in .claude-flow/horizons/aether-arena-aa.json",
-        "Memory stored in horizons namespace under key horizon-aether-arena-aa",
-        "Session check-in record stored in horizon-sessions namespace"
-      ]
-    }
-  ]
-}
@@ -1,96 +0,0 @@
-name: AetherArena harness gate (ADR-149)
-
-# Runs the AetherArena scoring harness as a PR build gate. Every PR that touches
-# the scorer, the metrics, or the benchmark scaffold must keep the deterministic
-# score hash stable (ADR-149 §2.5 determinism_gate). If the scoring maths changes,
-# the hash moves and this gate fails until `expected_score.sha256` is regenerated
-# and reviewed — so scorer drift can never land silently.
-#
-# This is the "a PR that runs the harness as part of the build process" requirement.
-
-on:
-  pull_request:
-    paths:
-      - 'v2/crates/wifi-densepose-train/src/ruview_metrics.rs'
-      - 'v2/crates/wifi-densepose-train/src/ablation.rs'
-      - 'v2/crates/wifi-densepose-train/src/bin/aa_score_runner.rs'
-      - 'aether-arena/**'
-      - '.github/workflows/aether-arena-harness.yml'
-  push:
-    branches: ['feat/adr-149-aether-arena']
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  pull-requests: write
-
-jobs:
-  harness-gate:
-    name: Run AA scorer harness (determinism gate)
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: v2
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-
-      - name: Install Rust toolchain
-        run: rustup show && rustc --version
-
-      - name: Cache cargo
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cargo/registry
-            ~/.cargo/git
-            v2/target
-          key: aa-harness-${{ runner.os }}-${{ hashFiles('v2/Cargo.lock') }}
-
-      # 1. Build the pure-Rust scorer (no torch / no GPU → fast PR gate).
-      - name: Build AA score runner
-        run: cargo build -p wifi-densepose-train --bin aa_score_runner --no-default-features
-
-      # 2. Determinism gate: the committed expected hash must still match. A
-      #    non-zero exit here fails the PR.
-      - name: Run determinism gate
-        run: cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features
-
-      # 3. Repeatability analysis (witness chain): the harness must produce one
-      #    identical proof hash across many runs — any nondeterminism fails here.
-      - name: Repeatability analysis (16 runs)
-        run: cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --repeat 16
-
-      # 4. Real-scoring smoke: score a sample prediction against the public smoke
-      #    split, exercising the actual model-scoring path (not just the fixture).
-      - name: Real-scoring smoke test
-        run: |
-          cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- \
-            --split ../aether-arena/fixtures/smoke_split.json \
-            --pred  ../aether-arena/fixtures/smoke_pred.json --json
-
-      # 5. Witness ledger chain integrity: the append-only results ledger must
-      #    verify (every prev_hash link + row_hash intact = no silent edits).
-      - name: Verify witness ledger chain
-        working-directory: aether-arena/ledger
-        run: python3 ledger_tools.py verify
-
-      # 6. Emit the witness row + repeatability into the PR run summary.
-      - name: Witness row → job summary
-        if: always()
-        run: |
-          ROW=$(cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --json)
-          REP=$(cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --repeat 16)
-          {
-            echo "## AetherArena harness gate (witness chain)"
-            echo ""
-            echo "Deterministic witness (ADR-149 §2.2 / proof + repeatability):"
-            echo '```json'
-            echo "$ROW"
-            echo "$REP"
-            echo '```'
-            echo ""
-            echo "If the determinism gate failed, the scoring maths changed: regenerate with"
-            echo '`cargo run -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --generate-hash > aether-arena/fixtures/expected_score.sha256` and review the diff.'
-          } >> "$GITHUB_STEP_SUMMARY"
@@ -1,199 +0,0 @@
-name: Bench Regression Guard
-
-# Sub-deliverable 8.3 of the benchmark/optimization milestone.
-#
-# HONEST SCOPE (read this before assuming this gates on timing):
-#   * The `bench-compile` job is a REAL, HARD-FAILING regression gate. It runs
-#     `cargo bench --no-default-features --no-run`, which type-checks and links
-#     EVERY criterion bench in the v2/ workspace without running a single
-#     measurement. Benches are not part of `cargo test`, so they silently
-#     bit-rot when a public API they call changes — this job catches that the
-#     moment it happens. This is the part of this workflow that can fail a PR.
-#
-#   * The `bench-fast-run` job runs a small, curated subset of pure-CPU benches
-#     in criterion "quick mode" (short warm-up / measurement / 10 samples) and
-#     is INFORMATIONAL ONLY (`continue-on-error: true`). It does NOT gate on
-#     timing. Wall-clock timings on shared GitHub-hosted runners vary by
-#     2-3x run-to-run (noisy neighbours, CPU throttling, no pinned frequency),
-#     so a hard ">X ms" threshold here would flake constantly and teach
-#     everyone to ignore it. We deliberately do not pretend to do timing
-#     regression-gating we cannot deliver reliably. The numbers are surfaced in
-#     the job log + uploaded as an artifact for humans to eyeball trends.
-#
-# WHY NO criterion --baseline COMPARE GATE:
-#   criterion's `--save-baseline` / `--baseline` compare is the textbook
-#   regression mechanism, but it only produces a trustworthy verdict when the
-#   baseline and the candidate were measured on the SAME hardware under the SAME
-#   conditions. GitHub-hosted runners give neither (the baseline commit and the
-#   PR commit land on different physical machines). Committing a baseline JSON
-#   measured on one runner and comparing a different runner against it would
-#   manufacture false regressions. If/when these benches run on a dedicated,
-#   frequency-pinned self-hosted runner, a `--baseline` compare with a generous
-#   (>2x) noise floor becomes honest and can be added then. Until then,
-#   compile-verify + informational-run is the honest gate.
-
-on:
-  push:
-    branches: [ main, develop, 'feat/*' ]
-    paths:
-      - 'v2/crates/**/benches/**'
-      - 'v2/crates/**/Cargo.toml'
-      - 'v2/crates/**/src/**'
-      - 'v2/Cargo.toml'
-      - 'v2/Cargo.lock'
-      - '.github/workflows/bench-regression.yml'
-  pull_request:
-    paths:
-      - 'v2/crates/**/benches/**'
-      - 'v2/crates/**/Cargo.toml'
-      - 'v2/crates/**/src/**'
-      - 'v2/Cargo.toml'
-      - 'v2/Cargo.lock'
-      - '.github/workflows/bench-regression.yml'
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-env:
-  CARGO_TERM_COLOR: always
-  # Debuginfo is useless in CI and the 38-crate workspace target dir otherwise
-  # exhausts the runner disk (mirrors ci.yml's rust-tests job). The bench
-  # profile inherits release + debug = true (v2/Cargo.toml [profile.bench]);
-  # force it off so the link step does not run out of space.
-  CARGO_PROFILE_BENCH_DEBUG: "0"
-  CARGO_PROFILE_RELEASE_DEBUG: "0"
-
-jobs:
-  # ── HARD GATE: every bench must still compile + link ─────────────────────
-  bench-compile:
-    name: bench compile-verify (--no-run)
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout (recursive — wifi-densepose-rufield path-deps vendor/rufield)
-        uses: actions/checkout@v4
-        with:
-          # The workspace includes `wifi-densepose-rufield`, which path-deps the
-          # `vendor/rufield` submodule crates. Without a recursive checkout the
-          # whole workspace fails to resolve before any bench is built.
-          submodules: recursive
-
-      # The workspace pulls in `wifi-densepose-desktop` (Tauri v2) whose -sys
-      # crates need the GTK/WebKit/serial dev libraries via pkg-config, exactly
-      # as ci.yml's rust-tests job documents. A `--workspace` bench build links
-      # the whole graph, so these are required here too.
-      - name: Install Tauri / GTK / serial system dev libraries
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends \
-            libglib2.0-dev \
-            libgtk-3-dev \
-            libsoup-3.0-dev \
-            libjavascriptcoregtk-4.1-dev \
-            libwebkit2gtk-4.1-dev \
-            libayatana-appindicator3-dev \
-            librsvg2-dev \
-            libxdo-dev \
-            libudev-dev \
-            libdbus-1-dev \
-            libssl-dev \
-            pkg-config
-
-      - name: Install Rust toolchain
-        uses: dtolnay/rust-toolchain@stable
-
-      - name: Cache cargo (Swatinem/rust-cache)
-        uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: v2
-          # Distinct cache scope from ci.yml's rust-tests so the bench profile
-          # artifacts (release+opt) do not evict the test profile cache.
-          key: bench-regression
-
-      # The core regression guard. `--no-run` compiles + links every bench
-      # target in the workspace's DEFAULT feature set but runs no measurement,
-      # so it is deterministic and fast-ish (build only). A bench that no longer
-      # compiles — because a type/signature it calls changed and nobody updated
-      # the bench — fails the build here. `--no-default-features` is the
-      # workspace's standard gate flag (openblas/tch/ort/onnx stay opt-out).
-      - name: Compile all workspace benches (default features)
-        working-directory: v2
-        run: cargo bench --workspace --no-default-features --no-run
-
-      # Feature-gated benches are skipped by the default build above because
-      # their `[[bench]]` entries carry `required-features`. Compile the ones we
-      # can guard so they are also covered against bit-rot.
-      #   * cir → wifi-densepose-signal/benches/cir_bench.rs (ADR-134). The
-      #     `cir` feature is pure-Rust (`cir = []`), so it builds on the stock
-      #     runner and is a real, hard-failing guard like the step above.
-      #
-      # NOT guarded here (honest scope):
-      #   * crv → wifi-densepose-ruvector/benches/crv_bench.rs. The `crv` feature
-      #     pulls the crates.io dependency `ruvector-crv 0.1.1`, which currently
-      #     FAILS to compile on stable (E0308 type mismatch in its own
-      #     `stage_iii.rs` — an UPSTREAM bug, unrelated to bench bit-rot).
-      #     Adding a hard `--features crv` compile step would make this workflow
-      #     red for a reason this gate is not meant to police. Re-add this step
-      #     once `ruvector-crv` ships a fixed release. (mqtt/onnx benches are
-      #     likewise left to their own crate workflows.)
-      - name: Compile feature-gated benches (cir)
-        working-directory: v2
-        run: cargo bench -p wifi-densepose-signal --no-default-features --features cir --bench cir_bench --no-run
-
-  # ── INFORMATIONAL: run a curated fast subset (never gates) ───────────────
-  bench-fast-run:
-    name: bench fast-run (informational, non-gating)
-    runs-on: ubuntu-latest
-    # NEVER fail the workflow on this job — timings are noise-prone on shared
-    # runners (see header). It exists to surface trends for humans, not to gate.
-    continue-on-error: true
-    needs: [bench-compile]
-    steps:
-      - name: Checkout (recursive)
-        uses: actions/checkout@v4
-        with:
-          submodules: recursive
-
-      - name: Install Rust toolchain
-        uses: dtolnay/rust-toolchain@stable
-
-      - name: Cache cargo (Swatinem/rust-cache)
-        uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: v2
-          key: bench-regression
-
-      # Curated subset = pure-CPU, fast, dependency-light criterion benches that
-      # finish in seconds under quick-mode flags. Each is targeted by `--bench`
-      # (NOT a bare `cargo bench -p`) because the crates' lib targets use the
-      # libtest harness, which rejects criterion's CLI flags (--warm-up-time
-      # etc.) and aborts the run. Quick-mode: 1s warm-up, 2s measure, 10 samples.
-      - name: nvsim pipeline_throughput (quick)
-        working-directory: v2
-        run: |
-          mkdir -p ../bench-out
-          cargo bench -p nvsim --no-default-features --bench pipeline_throughput -- \
-            --warm-up-time 1 --measurement-time 2 --sample-size 10 \
-            | tee ../bench-out/nvsim_pipeline_throughput.txt
-
-      - name: ruvector sketch_bench (quick)
-        working-directory: v2
-        run: |
-          cargo bench -p wifi-densepose-ruvector --no-default-features --bench sketch_bench -- \
-            --warm-up-time 1 --measurement-time 2 --sample-size 10 \
-            | tee ../bench-out/ruvector_sketch_bench.txt
-
-      - name: ruvector fusion_bench (quick)
-        working-directory: v2
-        run: |
-          cargo bench -p wifi-densepose-ruvector --no-default-features --bench fusion_bench -- \
-            --warm-up-time 1 --measurement-time 2 --sample-size 10 \
-            | tee ../bench-out/ruvector_fusion_bench.txt
-
-      - name: Upload informational bench logs
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: bench-fast-run-logs
-          path: bench-out/
-          if-no-files-found: warn
@@ -53,8 +53,6 @@ jobs:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Install Rust toolchain
        uses: dtolnay/rust-toolchain@stable
@@ -42,8 +42,6 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Determine deployment environment
      id: determine-env
@@ -88,8 +86,6 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up kubectl
      uses: azure/setup-kubectl@v3
@@ -136,8 +132,6 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up kubectl
      uses: azure/setup-kubectl@v3
@@ -29,7 +29,6 @@ jobs:
      continue-on-error: true
      uses: actions/checkout@v4
      with:
-        submodules: recursive
        fetch-depth: 0

    - name: Set up Python
@@ -83,13 +82,6 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
-      with:
-        submodules: recursive
-      # ADR-262 P1: `wifi-densepose-rufield` path-deps the `vendor/rufield`
-      # submodule. Without a recursive checkout the workspace build fails to
-      # resolve those path deps in CI even though it passes locally.
-      with:
-        submodules: recursive

    # `wifi-densepose-desktop` is a Tauri v2 app — `glib-sys`, `gtk-sys`,
    # `webkit2gtk-sys`, etc. need the Linux dev libraries via pkg-config or the
@@ -116,36 +108,23 @@ jobs:
    - name: Install Rust toolchain
      uses: dtolnay/rust-toolchain@stable

-    # Swatinem/rust-cache replaces a naive `actions/cache` of the whole
-    # `v2/target`. That manual cache of a 38-crate target dir (multi-GB) was an
-    # intermittent failure source — several CI runs this cycle died at the
-    # cache/setup step (after toolchain install, before "Run Rust tests"),
-    # needing a rerun. rust-cache is purpose-built for Rust: it caches the
-    # registry + git + a pruned target, evicts stale deps, and restores far more
-    # reliably (and faster) on large workspaces. `workspaces: v2` points it at
-    # the v2/ cargo workspace (keys on v2/Cargo.lock, caches v2/target).
-    - name: Cache cargo (Swatinem/rust-cache)
-      uses: Swatinem/rust-cache@v2
+    - name: Cache cargo
+      uses: actions/cache@v4
      with:
-        workspaces: v2
+        path: |
+          ~/.cargo/registry
+          ~/.cargo/git
+          v2/target
+        key: ${{ runner.os }}-cargo-${{ hashFiles('v2/Cargo.lock') }}
+        restore-keys: |
+          ${{ runner.os }}-cargo-

-    # The 38-crate workspace debug build exhausts the runner's disk when built
-    # with full debuginfo (observed: "final link failed: No space left on
-    # device" once the engine/benchmark crates landed; the same tree's local
-    # debug target measured 151 GB). Debuginfo is useless in CI — tests either
-    # pass or print their failure — so build without it; target shrinks ~5-10x.
    - name: Run Rust tests
      working-directory: v2
-      env:
-        CARGO_PROFILE_DEV_DEBUG: "0"
-        CARGO_PROFILE_TEST_DEBUG: "0"
      run: cargo test --workspace --no-default-features

    - name: Run ADR-147 worldmodel tests
      working-directory: v2
-      env:
-        CARGO_PROFILE_DEV_DEBUG: "0"
-        CARGO_PROFILE_TEST_DEBUG: "0"
      run: cargo test -p wifi-densepose-worldmodel --no-default-features

    # ADR-134 CIR tests are behind the `cir` feature so the bench dependency
@@ -210,8 +189,6 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up Python ${{ matrix.python-version }}
      continue-on-error: true
@@ -277,8 +254,6 @@ jobs:
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up Python
      uses: actions/setup-python@v6
@@ -290,45 +265,23 @@ jobs:
      run: |
        python -m pip install --upgrade pip
        pip install -r requirements.txt
-        pip install pytest   # the perf suite is pytest, not locust
+        pip install locust

-    # No "Start application" step: the gated test (test_frame_budget.py) drives
-    # the CSIProcessor pipeline in-process and makes no HTTP calls, so the old
-    # uvicorn server + `sleep 10` were dead weight — they only existed for the
-    # now-excluded api_throughput/inference_speed tests, and on every run dumped
-    # ~50 misleading "router requires hardware setup" ERROR lines for a server
-    # no test touched. MOCK_POSE_DATA is server-only and unused here.
-
-    - name: Run performance tests
+    - name: Start application
      working-directory: archive/v1
      run: |
-        # Gate only on the genuine, deterministic perf guard:
-        # test_frame_budget.py times the *real* CSIProcessor pipeline against
-        # the ADR 50 ms per-frame budget (single-frame, p95 over 100 frames,
-        # +Doppler) — a true regression signal.
-        #
-        # test_api_throughput.py / test_inference_speed.py are excluded: every
-        # test there is a TDD red-phase stub (suffix `_should_fail_initially`)
-        # that times a *mock that sleeps* — meaningless as a perf signal, with
-        # machine-dependent wall-clock asserts (e.g. `actual_rps >= 40`,
-        # `batch_time < individual_time`) that are inherently flaky on shared
-        # CI runners, plus a cross-class fixture-scope bug. Forcing them green
-        # would be manufacturing a false signal; they stay in-repo for local
-        # TDD but do not gate CI until the underlying features are implemented.
-        #
-        # `python -m pytest` (not the bare `pytest` script) puts the cwd
-        # (archive/v1) on sys.path so `from src.core...` resolves — the bare
-        # script omits cwd and raises ModuleNotFoundError: No module named 'src'.
-        # -o addopts="" drops the root pyproject's --cov/--cov-fail-under=100.
-        python -m pytest tests/performance/test_frame_budget.py \
-          -o addopts="" -v --junitxml=perf-junit.xml
+        uvicorn src.api.main:app --host 0.0.0.0 --port 8000 &
+        sleep 10
+
+    - name: Run performance tests
+      run: |
+        locust -f tests/performance/locustfile.py --headless --users 50 --spawn-rate 5 --run-time 60s --host http://localhost:8000

    - name: Upload performance results
-      if: always()
      uses: actions/upload-artifact@v4
      with:
        name: performance-results
-        path: archive/v1/perf-junit.xml
+        path: locust_report.html

  # Docker Build and Test
  # NOTE: the canonical Docker build for the sensing-server is now
@@ -347,8 +300,6 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up Docker Buildx
      continue-on-error: true
@@ -416,13 +367,9 @@ jobs:
    runs-on: ubuntu-latest
    needs: [docker-build]
    if: github.ref == 'refs/heads/main'
-    permissions:
-      contents: write   # gh-pages deploy needs write (GITHUB_TOKEN is read-only by default -> 403)
    steps:
    - name: Checkout code
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up Python
      uses: actions/setup-python@v6
@@ -437,8 +384,6 @@ jobs:

    - name: Generate OpenAPI spec
      working-directory: archive/v1
-      env:
-        MOCK_POSE_DATA: "true"   # no CSI hardware in CI
      run: |
        python -c "
        from src.api.main import app
@@ -449,7 +394,6 @@ jobs:

    - name: Deploy to GitHub Pages
      uses: peaceiris/actions-gh-pages@v4
-      continue-on-error: true   # openapi generation above is the real validation; deploy is best-effort (Pages may be disabled)
      with:
        github_token: ${{ secrets.GITHUB_TOKEN }}
        publish_dir: ./docs
@@ -35,8 +35,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Fetch /traffic/clones + /traffic/views from GitHub
        env:
@@ -28,8 +28,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Setup Rust
        uses: dtolnay/rust-toolchain@stable
@@ -80,8 +78,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Setup Rust
        uses: dtolnay/rust-toolchain@stable
@@ -149,8 +145,6 @@ jobs:
      vars.HAS_GCP_CREDENTIALS == 'true'
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Download x86_64 artifact
        uses: actions/download-artifact@v4
@@ -20,8 +20,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - uses: dtolnay/rust-toolchain@stable
        with: { targets: wasm32-unknown-unknown }
@@ -26,8 +26,6 @@ jobs:
    steps:
      - name: Checkout main
        uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Install Rust + wasm32 target
        uses: dtolnay/rust-toolchain@stable
@@ -28,8 +28,6 @@ jobs:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Setup Node.js
        uses: actions/setup-node@v6
@@ -85,8 +83,6 @@ jobs:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Setup Node.js
        uses: actions/setup-node@v6
@@ -135,8 +131,6 @@ jobs:
    steps:
      - name: Checkout
        uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Download all artifacts
        uses: actions/download-artifact@v4
@@ -22,8 +22,6 @@ jobs:
    if: github.ref_type == 'tag'
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
      - name: Check firmware version.txt == tag
        run: |
          # Tag form: vX.Y.Z-esp32  →  expect version.txt to contain X.Y.Z
@@ -73,8 +71,6 @@ jobs:

    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Build firmware (${{ matrix.variant }})
        working-directory: firmware/esp32-csi-node
@@ -100,8 +100,6 @@ jobs:

    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Download QEMU artifact
        uses: actions/download-artifact@v4
@@ -216,8 +214,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Install clang
        run: |
@@ -267,8 +263,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Install NVS generator
        run: pip install esp-idf-nvs-partition-gen
@@ -323,8 +317,6 @@ jobs:

    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Download QEMU artifact
        uses: actions/download-artifact@v4
@@ -22,8 +22,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - uses: actions/setup-python@v6
        with:
@@ -41,8 +41,6 @@ jobs:

    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Install mosquitto + clients and start with allow_anonymous
        run: |
@@ -26,8 +26,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - uses: docker/setup-buildx-action@v3

@@ -76,8 +76,6 @@ jobs:
    runs-on: ${{ matrix.os }}
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive

      # Linux aarch64 needs QEMU for cross-build on x86_64 runners.
      - name: Set up QEMU
@@ -123,8 +121,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
      - name: Install maturin
        run: pip install maturin>=1.7
      - name: Build sdist
@@ -148,8 +144,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
      - uses: actions/setup-python@v5
        with:
          python-version: '3.12'
@@ -29,8 +29,6 @@ jobs:
    steps:
      - name: Checkout main
        uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Stage viewer for Pages
        run: |
@@ -40,8 +40,6 @@ jobs:
          - { label: 'full+train',       flags: '--features full,train' }
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
      - uses: dtolnay/rust-toolchain@stable
      - name: Cache cargo
        uses: actions/cache@v4
@@ -62,16 +60,8 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      # v2/rust-toolchain.toml pins channel "1.89" with profile "minimal" (no
-      # clippy). dtolnay@stable installs clippy on the floating "stable"
-      # toolchain, but the override makes cargo use the separate "1.89"
-      # toolchain — so `cargo clippy` errors "cargo-clippy is not installed for
-      # 1.89". Install clippy on the pinned toolchain that cargo actually uses.
      - uses: dtolnay/rust-toolchain@stable
        with:
-          toolchain: "1.89"
          components: clippy
      - name: Cache cargo
        uses: actions/cache@v4
@@ -97,8 +87,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
      - uses: dtolnay/rust-toolchain@stable
      - name: Cache cargo
        uses: actions/cache@v4
@@ -133,8 +121,6 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
      - name: publish = false is present (no accidental crates.io publish)
        run: |
          CARGO=v2/crates/ruview-swarm/Cargo.toml
@@ -28,7 +28,6 @@ jobs:
      continue-on-error: true
      uses: actions/checkout@v4
      with:
-        submodules: recursive
        fetch-depth: 0

    - name: Set up Python
@@ -47,10 +46,7 @@ jobs:

    - name: Run Bandit security scan
      run: |
-        # The Python codebase lives under archive/v1/src (it moved there when
-        # the runtime was rewritten in Rust). Scanning `src/` matched nothing,
-        # so this SAST step was a silent no-op.
-        bandit -r archive/v1/src/ -f sarif -o bandit-results.sarif
+        bandit -r src/ -f sarif -o bandit-results.sarif
      continue-on-error: true

    - name: Upload Bandit results to GitHub Security
@@ -61,20 +57,22 @@ jobs:
        sarif_file: bandit-results.sarif
        category: bandit

-    # Removed the deprecated `returntocorp/semgrep-action@v1` step: it was
-    # redundant (the pip `semgrep --sarif` below is what feeds GitHub Security;
-    # the action only pushed to the Semgrep cloud app via SEMGREP_APP_TOKEN) and
-    # it pulled `returntocorp/semgrep-agent:v1` from Docker Hub on every run,
-    # which intermittently timed out and turned this check red. The pip semgrep
-    # (installed above) needs no Docker pull. The action's `p/docker` +
-    # `p/kubernetes` rulesets are folded into the command below so coverage is
-    # preserved.
-    - name: Run Semgrep + generate SARIF
+    - name: Run Semgrep security scan
+      continue-on-error: true
+      uses: returntocorp/semgrep-action@v1
+      with:
+        config: >-
+          p/security-audit
+          p/secrets
+          p/python
+          p/docker
+          p/kubernetes
+      env:
+        SEMGREP_APP_TOKEN: ${{ secrets.SEMGREP_APP_TOKEN }}
+        
+    - name: Generate Semgrep SARIF
      run: |
-        semgrep \
-          --config=p/security-audit --config=p/secrets --config=p/python \
-          --config=p/docker --config=p/kubernetes \
-          --sarif --output=semgrep.sarif archive/v1/src/
+        semgrep --config=p/security-audit --config=p/secrets --config=p/python --sarif --output=semgrep.sarif src/
      continue-on-error: true

    - name: Upload Semgrep results to GitHub Security
@@ -98,8 +96,6 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up Python
      continue-on-error: true
@@ -167,8 +163,6 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up Docker Buildx
      continue-on-error: true
@@ -250,8 +244,6 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Run Checkov IaC scan
      continue-on-error: true
@@ -314,7 +306,6 @@ jobs:
      continue-on-error: true
      uses: actions/checkout@v4
      with:
-        submodules: recursive
        fetch-depth: 0

    - name: Run TruffleHog secret scan
@@ -349,8 +340,6 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Set up Python
      continue-on-error: true
@@ -388,8 +377,6 @@ jobs:
    - name: Checkout code
      continue-on-error: true
      uses: actions/checkout@v4
-      with:
-        submodules: recursive

    - name: Check security policy files
      continue-on-error: true
@@ -30,8 +30,6 @@ jobs:
    steps:
      - name: Checkout main
        uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Stage demos for Pages
        run: |
@@ -7,7 +7,6 @@ on:
      - 'archive/v1/src/core/**'
      - 'archive/v1/src/hardware/**'
      - 'archive/v1/data/proof/**'
-      - 'archive/v1/requirements-lock.txt'
      - '.github/workflows/verify-pipeline.yml'
  pull_request:
    branches: [ main, master ]
@@ -15,7 +14,6 @@ on:
      - 'archive/v1/src/core/**'
      - 'archive/v1/src/hardware/**'
      - 'archive/v1/data/proof/**'
-      - 'archive/v1/requirements-lock.txt'
      - '.github/workflows/verify-pipeline.yml'
  workflow_dispatch:

@@ -30,8 +28,6 @@ jobs:
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
-        with:
-          submodules: recursive

      - name: Set up Python ${{ matrix.python-version }}
        uses: actions/setup-python@v6
@@ -16,15 +16,6 @@ firmware/esp32-csi-node/sdkconfig.defaults.bak
 # ESP-IDF set-target backup (local only)
 firmware/esp32-hello-world/sdkconfig.old

-# Host-built firmware test binaries (compiled from test/*.c, not source)
-firmware/esp32-csi-node/test/test_adr110
-firmware/esp32-csi-node/test/test_vitals
-firmware/esp32-csi-node/test/fuzz_serialize
-firmware/esp32-csi-node/test/fuzz_edge
-firmware/esp32-csi-node/test/fuzz_nvs
-firmware/esp32-csi-node/test/*.exe
-firmware/esp32-csi-node/test/*.obj
-
 # Claude Flow swarm runtime state
 .swarm/

@@ -270,10 +261,3 @@ v2/crates/rvcsi-node/*.node
 v2/crates/rvcsi-node/binding.js
 v2/crates/rvcsi-node/binding.d.ts
 v2/crates/rvcsi-node/npm/
-
-# AetherArena private optimization staging — never published until reviewed
-aether-arena/staging/
-
-# MM-Fi benchmark dataset archives — large data, fetch separately, never commit
-assets/MM-Fi/E0*.zip
-assets/MM-Fi/*.zip
@@ -14,10 +14,3 @@
 	path = vendor/rvcsi
 	url = https://github.com/ruvnet/rvcsi
 	branch = main
-[submodule "v2/crates/ruv-neural"]
-	path = v2/crates/ruv-neural
-	url = https://github.com/ruvnet/ruv-neural.git
-	branch = main
-[submodule "vendor/rufield"]
-	path = vendor/rufield
-	url = https://github.com/ruvnet/rufield
@@ -10,20 +10,17 @@ Dual codebase: Python v1 (`v1/`) and Rust port (`v2/`).
 | `wifi-densepose-core` | Core types, traits, error types, CSI frame primitives |
 | `wifi-densepose-signal` | SOTA signal processing + RuvSense multistatic sensing (16 modules) |
 | `wifi-densepose-nn` | Neural network inference (ONNX, PyTorch, Candle backends) |
-| `wifi-densepose-train` | Training pipeline with ruvector integration + ruview_metrics; MAE pretraining recipe (`mae.rs`, ADR-152 §2.3) + WiFlow-STD port (`wiflow_std/`, tch-gated) |
+| `wifi-densepose-train` | Training pipeline with ruvector integration + ruview_metrics |
 | `wifi-densepose-mat` | Mass Casualty Assessment Tool — disaster survivor detection |
-| `wifi-densepose-hardware` | ESP32 aggregator, TDM protocol, channel hopping firmware; `ieee80211bf/` 802.11bf forward-compat protocol model (ADR-153) |
+| `wifi-densepose-hardware` | ESP32 aggregator, TDM protocol, channel hopping firmware |
 | `wifi-densepose-ruvector` | RuVector v2.0.4 integration + cross-viewpoint fusion (5 modules) |
 | `wifi-densepose-wasm` | WebAssembly bindings for browser deployment |
-| `wifi-densepose-cli` | CLI tool (`wifi-densepose` binary) — `calibrate`/`calibrate-serve`/`enroll`/`train-room`/`room-watch` + MAT (MAT gated behind the `mat` feature; build `--no-default-features` for the aarch64/appliance calibration binary) |
-| `wifi-densepose-calibration` | ADR-151 per-room calibration & specialist training — `baseline → enroll → extract → train` → bank of small specialists (presence/posture/breathing/heartbeat/restlessness/anomaly) + multistatic fusion; pure Rust, edge-deployable |
+| `wifi-densepose-cli` | CLI tool (`wifi-densepose` binary) |
 | `wifi-densepose-sensing-server` | Lightweight Axum server for WiFi sensing UI |
 | `wifi-densepose-wifiscan` | Multi-BSSID WiFi scanning (ADR-022) |
 | `wifi-densepose-vitals` | ESP32 CSI-grade vital sign extraction (ADR-021) |
 | `nvsim` | Deterministic NV-diamond magnetometer pipeline simulator (ADR-089) — standalone leaf, WASM-ready |
 | `vendor/rvcsi` (submodule) | **rvCSI** — edge RF sensing runtime (ADR-095/096): 9 crates (`rvcsi-core`/`-dsp`/`-events`/`-adapter-file`/`-adapter-nexmon`/`-ruvector`/`-runtime`/`-node`/`-cli`). Lives in its own repo ([github.com/ruvnet/rvcsi](https://github.com/ruvnet/rvcsi)), vendored here under `vendor/rvcsi`, published to crates.io as `rvcsi-* 0.3.x` and to npm as `@ruv/rvcsi`. Not a `v2/` workspace member — depend on the published crates (or the submodule's `crates/rvcsi-*` paths). Normalized `CsiFrame`/`CsiWindow`/`CsiEvent` schema, validate-before-FFI, reusable DSP, typed confidence-scored events, the napi-c Nexmon shim (real nexmon_csi `.pcap` from a Raspberry Pi 5 / 4 / 3B+ — BCM43455c0), the napi-rs SDK, the `rvcsi` CLI, a Claude Code plugin. |
-| `vendor/rufield` (submodule) | **RuField MFS** — the open spec for camera-free multimodal field sensing (ADR-260). A common `FieldEvent`/`FieldTensor`/`FusionGraph`/`PrivacyClass`/`ProvenanceReceipt` model *above* WiFi CSI/CIR/BFLD, UWB, BLE Channel Sounding, mmWave radar, ultrasound, subsonic, infrared, and quantum sensors. Lives in its own repo ([github.com/ruvnet/rufield](https://github.com/ruvnet/rufield)), vendored here under `vendor/rufield`. Not a `v2/` workspace member. v0.1 reference stack = 7 crates (`rufield-core`/`-provenance`/`-privacy`/`-adapters`/`-fusion`/`-bench`/`-viewer`), 72 tests/0 failed; `rufield-viewer` is an Axum + vanilla-JS read-only dashboard (`cargo run -p rufield-viewer`) completing ADR-260 §27.9. The WiFi-CSI modality is now **real-replay-backed** via `CsiReplayAdapter` (ingests real captured `.csi.jsonl` → fused presence/breathing inferences; replay-from-file, unlabeled CSI-variance proxy, not validated accuracy); mmWave/thermal + all synthetic-bench F1 numbers remain **SYNTHETIC** (no live hardware — live streaming + labeled accuracy are roadmap). |
-| `wifi-densepose-rufield` | ADR-262 P1 **anti-corruption bridge** — converts RuView WiFi-CSI sensing output (`SensingSnapshot` mirroring `SensingUpdate` + `TrustedOutput`, owned primitives, no dep on `wifi-densepose-sensing-server`) into **signed RuField `FieldEvent`s** (`Modality::WifiCsi`, real `timestamp_ns`, sha256 + ed25519 provenance, `synthetic=false`). The single coupling point between RuView and the standalone RuField MFS spec (§5.4); path-deps the `vendor/rufield` submodule crates (`rufield-core`/`-provenance`/`-privacy`/`-fusion`). **Critical §3.3 privacy mapping** (`map_privacy`): maps RuView class → RuField P0–P5 by **information content, never byte value**, fail-closed (`Derived → P4/P5`, never P1; `demoted` floors to ≥ P2). 15 tests / 0 failed (round-trip / `is_fusable` / fusion-ingest / privacy-safety / determinism). P1 plumbing — not wired into the live server (P3), no accuracy claim. |
 | `ruview-swarm` | Drone swarm control system (ADR-148) — hierarchical-mesh topology, Raft consensus, MARL, CSI sensing payload, MAVLink/PX4 compat, Ruflo AI-agent integration |

 ### RuvSense Modules (`signal/src/ruvsense/`)
@@ -75,8 +72,6 @@ All 5 ruvector crates integrated in workspace:
 - ADR-031: RuView sensing-first RF mode (Proposed)
 - ADR-032: Multistatic mesh security hardening (Proposed)
 - ADR-148: Drone swarm control system / `ruview-swarm` (In Progress)
- ADR-152: WiFi-Pose SOTA 2026 intake — geometry conditioning, WiFlow-STD benchmark (measurement (a) complete: claims MEASURED-EQUIVALENT at ~96% PCK@20), MAE recipe (Proposed; §2.1–2.3, 2.6 implemented)
- ADR-153: IEEE 802.11bf-2025 forward-compatibility protocol model (Accepted — amends ADR-152 §2.4)

 ### Supported Hardware

@@ -1,78 +0,0 @@
-# PROOF — reproduce every claim, or find the one we can't yet
-
-This project (RuView / wifi-densepose) has been publicly called "AI slop" and
-"fake." This document is the answer: **a skeptic can clone the repo, run one
-script, and have every headline claim either verified on their own machine or
-shown — explicitly — as "CLAIMED, not yet reproduced (here's exactly what it
-needs)."** Nothing below is asserted without a command you can run.
-
-```bash
-git clone https://github.com/ruvnet/RuView && cd RuView
-bash scripts/prove.sh          # core gate + the anti-slop assertion tests
-bash scripts/prove.sh --full   # also attempt the feature-gated subset
-```
-
-`prove.sh` exits 0 only if every **non-gated** claim passes. Gated claims never
-fail the run; they print the prerequisite (a GPU, a dataset, real hardware, a
-trained checkpoint) so you can reproduce them yourself.
-
-## Grading
-
- **MEASURED** — reproduced on our hardware, with the exact command recorded, and
-  pinned by a test that *fails on the pre-fix code*. `prove.sh` re-runs these.
- **CLAIMED** — cited from a source, or measured by the source, but not
-  reproduced in this repo's automated harness.
- **DATA-GATED / HARDWARE-GATED** — the *code path* is real and tested, but the
-  *accuracy/throughput claim* needs data or hardware we don't ship. We never
-  fabricate the number; the code carries a typed error or a `weights_trained`/
-  provenance flag instead.
-
-## The hard gate (run on any machine with Rust + Python)
-
-| Claim | Grade | Reproduce |
-|---|---|---|
-| Rust workspace: 3,128 tests, 0 failed | **MEASURED** | `cd v2 && cargo test --workspace --no-default-features` |
-| Deterministic CSI pipeline proof (bit-exact SHA-256) | **MEASURED** | `python archive/v1/data/proof/verify.py` → `VERDICT: PASS` |
-
-## Anti-slop assertion tests (each fails on the pre-fix code)
-
-| Claim | Grade | Test (run via `cargo test -p <crate> <name>`) |
-|---|---|---|
-| Fusion crafted-input DoS panics are closed (ADR-156 §2.2) | **MEASURED** | `wifi-densepose-ruvector :: triangulation_out_of_range_index_returns_none_no_panic` |
-| **The "Soul Signature" identity claim, honestly bounded:** on WiFi-only cardiac+respiratory channels two people are **not separable** (gap ≈ 0.0005) | **MEASURED** | `wifi-densepose-bfld :: cardiac_alone_cannot_separate_identity_matches_audit` |
-| OccWorld `predict()` is real (input-dependent), not random noise | **MEASURED** | `wifi-densepose-occworld-candle :: predict_is_deterministic_for_same_input` |
-| Pose runtime emits frames under its own default config (ADR-159 A1) | **MEASURED** | `cog-pose-estimation :: default_config_emits_frames_with_real_model` |
-| Person-count flags untrained classes — no count inflation (ADR-159 A2) | **MEASURED** | `cog-person-count :: untrained_class_argmax_is_flagged_low_confidence` |
-| Medical edge skills carry a "not a medical device" disclaimer (ADR-160 A1) | **MEASURED** | `wifi-densepose-wasm-edge :: a1_med_modules_have_clinical_disclaimer` (`--features std`) |
-| Survivor dedup 3→1, count-inflation killed (ADR-158 §2) | **MEASURED** | `wifi-densepose-mat :: test_identical_vitals_no_location_dedup_to_one` (`--features mat`) |
-
-## Measured performance (criterion; reproduce on your machine)
-
-| Claim | Grade | Reproduce |
-|---|---|---|
-| PSD FFT-planner cache 2.0–3.1×, DTW band 2.4–4.1× (ADR-154) | **MEASURED** | `cd v2 && cargo bench -p wifi-densepose-signal` |
-| fuse() double-clone removed ~2.17× marshalling (ADR-156) | **MEASURED** | `cd v2 && cargo bench -p wifi-densepose-ruvector --bench fusion_bench` |
-| zero-copy ORT input ~1.48× (ADR-155) | **MEASURED** | `cd v2 && cargo bench -p wifi-densepose-nn --features onnx --bench onnx_bench` |
-| pointcloud splats 9→2 passes ~1.24× (ADR-160 research) | **MEASURED** | `cd v2 && cargo bench -p wifi-densepose-pointcloud --bench splats_bench` |
-| native wlanapi multi-BSSID scan 9.74 Hz (vs netsh ~2 Hz) | **MEASURED (Windows)** | `cd v2 && cargo test -p wifi-densepose-wifiscan -- --ignored measure_native_scan_rate` |
-| wasm-edge `process_frame` hot-path latency (host proxy, ADR-163) | **MEASURED-on-host** (NOT the ESP32/WASM3 budget — needs hardware) | `cd v2/crates/wifi-densepose-wasm-edge && cargo bench --features std` |
-| cog steady-state CPU infer latency ~305 µs (ADR-163; NOT the manifest cold-start) | **MEASURED-on-host** | `cd v2 && cargo bench -p cog-person-count -p cog-pose-estimation --no-default-features --bench infer_bench` |
-
-## What we do NOT claim (the honest negatives — the strongest anti-slop signal)
-
-| Capability | Status |
-|---|---|
-| **Named person-identity from WiFi** | **NOT achieved, and measured why.** The §3.6 matcher is real, but identity does not lock on WiFi-only channels (gap 0.0005). DATA-GATED on a real enrollment feeding the AETHER/body-resonance channel — never done. No named-identity claim is made. |
-| WiFlow-STD ~96% PCK@20 | **CLAIMED-reproduced** on our RTX 5080 (`benchmarks/wiflow-std/RESULTS.md`); HARDWARE-GATED for you (needs an NVIDIA GPU + the MM-Fi dataset). The upstream *shipped checkpoint* was **REFUTED** (0.08% PCK) — we publish that. |
-| OccWorld trajectory accuracy | DATA-GATED on a trained checkpoint; `predict()` carries `weights_trained=false` until one is loaded — never silently faked. |
-| Edge-skill detection accuracy (seizure, weapon, affect, …) | UNVALIDATED — every such module is now disclaimer-gated as experimental/research; the DSP is real, the accuracy is not claimed. |
-| 802.11bf-2025 OTA conformance | No commodity silicon ships a conformant interface as of 2026; ours is a simulation-tested forward-compat protocol model, not a certified implementation. |
-
-## Provenance
-
-Every claim above traces to a committed ADR (`docs/adr/ADR-154`…`ADR-163`), a
-test, a criterion bench, `benchmarks/wiflow-std/RESULTS.md`, or
-`benchmarks/edge-latency/RESULTS.md`. The history
-includes published **retractions** (the 92.9% PCK retraction; the WiFlow-STD
-shipped-checkpoint refutation; the NV-diamond BOM reality check) — a faker hides
-failures; we commit them.
@@ -36,7 +36,7 @@ Built on [RuVector](https://github.com/ruvnet/ruvector/) and [Cognitum Seed](htt

 The system learns each environment locally using spiking neural networks that adapt in under 30 seconds, with multi-frequency mesh scanning across 6 WiFi channels that uses your neighbors' routers as free radar illuminators. Every measurement is cryptographically attested via an Ed25519 witness chain.

-RuView turns ordinary WiFi into a contactless sensor. A $9 ESP32 board reads the radio reflections off the people in a room, and a small pretrained model — published on Hugging Face at [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained) — tells you who's there, how they're breathing, and how their heart rate is trending. The model fits in 8 KB (4-bit quantized) and runs in microseconds on a Raspberry Pi. (The [v2 encoder](https://huggingface.co/ruvnet/wifi-densepose-pretrained) reports an honest, label-free held-out **temporal-triplet accuracy of 82.3%** — up from 66.4% raw; the older "100% presence" figure was measured on a single-class recording and has been retracted in favor of this.) No cameras, no wearables, no app on the user's phone.
+RuView turns ordinary WiFi into a contactless sensor. A $9 ESP32 board reads the radio reflections off the people in a room, and a small pretrained model — published on Hugging Face at [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained) — tells you who's there, how they're breathing, and how their heart rate is trending. The model fits in 8 KB (4-bit quantized), runs in microseconds on a Raspberry Pi, and reports 100% presence accuracy on the validation set. No cameras, no wearables, no app on the user's phone.

 ### Built for low-power edge applications

@@ -56,9 +56,9 @@ RuView turns ordinary WiFi into a contactless sensor. A $9 ESP32 board reads the
 > |------|-----|---------------|
 > | 🫁 **Breathing rate** | Bandpass 0.1–0.5 Hz on wrapped phase, circular variance, zero-crossing BPM ([#593](https://github.com/ruvnet/RuView/issues/593)) | 6–30 BPM, real-time |
 > | 💓 **Heart rate** | Bandpass 0.8–2.0 Hz, zero-crossing BPM | 40–120 BPM, real-time |
-> | 👤 **Presence detection** | Trained head on Hugging Face ([`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained); v2 encoder = 82.3% held-out temporal-triplet acc, honestly re-benchmarked) + a phase-variance fallback that needs no model | < 1 ms, ~30 s ambient calibration |
+> | 👤 **Presence detection** | Trained head on Hugging Face ([`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained), 100% validation accuracy) + a phase-variance fallback that needs no model | < 1 ms, ~30 s ambient calibration |
 > | 🧬 **CSI embeddings** | 128-dim contrastive encoder shipped on Hugging Face, 4-bit quantised variant fits in 8 KB | **164,183 emb/s** on M4 Pro |
-> | 🦴 **17-keypoint pose estimation** | `cog-pose-estimation` Cog v0.0.1 — signed aarch64 + x86_64 binaries on GCS, loads `pose_v1.safetensors` via Candle. Train your own from paired data in 2.1 s on an RTX 5080 ([ADR-101](docs/adr/ADR-101-pose-estimation-cog.md), [benchmarks](docs/benchmarks/pose-estimation-cog.md)). **SOTA on MM-Fi:** [`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose) hits **82.69% torso-PCK@20** (ensemble 83.59%), beating MultiFormer (72.25%) and CSI2Pose (68.41%) on the matched MM-Fi `random_split` protocol — self-corrected and auditable on [AetherArena](https://huggingface.co/spaces/ruvnet/aether-arena) | 8.4 ms cold-start on a Pi 5 |
+> | 🦴 **17-keypoint pose estimation** | `cog-pose-estimation` Cog v0.0.1 — signed aarch64 + x86_64 binaries on GCS, loads `pose_v1.safetensors` via Candle. Train your own from paired data in 2.1 s on an RTX 5080 ([ADR-101](docs/adr/ADR-101-pose-estimation-cog.md), [benchmarks](docs/benchmarks/pose-estimation-cog.md)) | 8.4 ms cold-start on a Pi 5 |
 > | 🚶 **Motion / activity** | Motion-band power + phase acceleration | Real-time |
 > | 🤸 **Fall detection** | Phase-acceleration threshold + 3-frame debounce + 5 s cooldown ([#263](https://github.com/ruvnet/RuView/issues/263)) | < 200 ms |
 > | 🧮 **Multi-person count** | Adaptive P95 normalisation + runtime-tunable dedup factor (`/api/v1/config/dedup-factor`, [#491](https://github.com/ruvnet/RuView/pull/491)). Six specialised learned counters available as Cogs: `occupancy-zones`, `elevator-count`, `queue-length`, `customer-flow`, `clean-room`, `person-matching` | Real-time, self-calibrating |
@@ -162,7 +162,7 @@ pip install "ruview[client]"              # or: pip install "wifi-densepose[clie

 ## 🤗 Pretrained model on Hugging Face

-Pretrained CSI weights live at [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained) — 12.2M training steps on 60K frames / 610K contrastive triplets, **82.3% held-out temporal-triplet accuracy** (up from 66.4% raw; the older "100% presence" figure was measured on a single-class recording and has been retracted), 4-bit quantized variant fits in 8 KB. The release includes a contrastive **CSI encoder** producing 128-dim embeddings (164,183 emb/s on M4 Pro) and a **presence-detection head**. Per-node LoRA adapters are included for environment-specific fine-tuning.
+Pretrained CSI weights live at [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained) — 12.2M training steps on 60K frames / 610K contrastive triplets, **100% presence accuracy** on the validation set, 4-bit quantized variant fits in 8 KB. The release includes a contrastive **CSI encoder** producing 128-dim embeddings (164,183 emb/s on M4 Pro) and a **presence-detection head**. Per-node LoRA adapters are included for environment-specific fine-tuning.

 ```bash
 # Download the model bundle
@@ -182,27 +182,7 @@ huggingface-cli download ruvnet/wifi-densepose-pretrained --local-dir models/wif

 **Quantization choices** (all in the HF repo): `model-q2.bin` (4 KB) · `model-q4.bin` ⭐ recommended (8 KB) · `model-q8.bin` (16 KB) · `model.safetensors` full (48 KB)

-The separate **17-keypoint pose-estimation model** is now published at [`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose) — **82.69% torso-PCK@20** on MM-Fi (single model) / **83.59%** (3-model ensemble + TTA), beating the prior published SOTA MultiFormer (72.25%) and CSI2Pose (68.41%) on the matched `random_split` protocol. See **Results & proof** below.
-
-### Results & proof
-
-| What | Where | Numbers |
-|------|-------|---------|
-| **MM-Fi pose model (SOTA)** | [`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose) | 82.69% torso-PCK@20 (single) · 83.59% (ensemble+TTA) · 75K-param micro variant 74.30% |
-| **AetherArena benchmark Space** | [`ruvnet/aether-arena`](https://huggingface.co/spaces/ruvnet/aether-arena) | self-correcting, auditable MM-Fi leaderboard |
-| **Full MM-Fi study (honest picture)** | [`docs/benchmarks/mmfi-wifi-sensing-study.md`](docs/benchmarks/mmfi-wifi-sensing-study.md) | pose + action; zero-shot cross-subject ~64%, +~30 s in-room calibration → 72.2% |
-| **Efficiency frontier** | [`docs/benchmarks/wifi-pose-efficiency-frontier.md`](docs/benchmarks/wifi-pose-efficiency-frontier.md) | SOTA-beating WiFi pose in a 20 KB int4 edge model |
-| **Pretrained encoder** | [`ruvnet/wifi-densepose-pretrained`](https://huggingface.co/ruvnet/wifi-densepose-pretrained) | 82.3% held-out temporal-triplet, 8 KB int4 |
-| **Reproducible proof (Trust Kill Switch)** | [`archive/v1/data/proof/verify.py`](archive/v1/data/proof/verify.py) + [`expected_features.sha256`](archive/v1/data/proof/expected_features.sha256) | one-command deterministic pipeline replay (SHA-256 of output vs published hash) |
-| **Benchmark-proof ADR** | [ADR-168](docs/adr/ADR-168-benchmark-proof.md) | how the numbers are produced and verified |
-| **Witness attestation** | [`docs/WITNESS-LOG-028.md`](docs/WITNESS-LOG-028.md) | 33-row capability attestation matrix with per-claim evidence |
-
-```bash
-# Reproduce the deterministic pipeline proof yourself (must print VERDICT: PASS):
-python archive/v1/data/proof/verify.py
-```
-
-Tracked in [#509](https://github.com/ruvnet/RuView/issues/509); see [ADR-079](docs/adr/ADR-079-camera-supervised-pose-finetune.md) phases P7–P9 for the camera-supervised fine-tune path.
+The separate **17-keypoint pose-estimation model** is not in this release — pipeline is implemented but keypoint weights are still pending. Tracked in [#509](https://github.com/ruvnet/RuView/issues/509); see [ADR-079](docs/adr/ADR-079-camera-supervised-pose-finetune.md) phases P7–P9.


 ## 🧩 Edge Module Catalog
@@ -501,7 +481,7 @@ Every WiFi signal that passes through a room creates a unique fingerprint of tha
 **What it does in plain terms:**
 - Turns any WiFi signal into a 128-number "fingerprint" that uniquely describes what's happening in a room
 - Learns entirely on its own from raw WiFi data — no cameras, no labeling, no human supervision needed
- Recognizes rooms, detects intruders, and classifies activities using only WiFi (named person-identity is an experimental, data-gated research capability — see below, not a shipped feature)
+- Recognizes rooms, detects intruders, identifies people, and classifies activities using only WiFi
 - Runs on an $8 ESP32 chip (the entire model fits in 55 KB of memory)
 - Produces both body pose tracking AND environment fingerprints in a single computation

@@ -512,7 +492,7 @@ Every WiFi signal that passes through a room creates a unique fingerprint of tha
 | **Self-supervised learning** | The model watches WiFi signals and teaches itself what "similar" and "different" look like, without any human-labeled data | Deploy anywhere — just plug in a WiFi sensor and wait 10 minutes |
 | **Room identification** | Each room produces a distinct WiFi fingerprint pattern | Know which room someone is in without GPS or beacons |
 | **Anomaly detection** | An unexpected person or event creates a fingerprint that doesn't match anything seen before | Automatic intrusion and fall detection as a free byproduct |
-| **Person re-identification** *(experimental, research)* | A real per-channel similarity matcher (Soul Signature §3.6, `wifi-densepose-bfld`); **measured** result: on WiFi-only cardiac+respiratory channels alone two people are *not* separable (gap ~0.0005) | Honest research capability — **named identity is not claimed** and is data-gated on enrollment with the decisive AETHER/body-resonance channel. See [#1021](https://github.com/ruvnet/RuView/issues/1021) |
+| **Person re-identification** | Each person disturbs WiFi in a slightly different way, creating a personal signature | Track individuals across sessions without cameras |
 | **Environment adaptation** | MicroLoRA adapters (1,792 parameters per room) fine-tune the model for each new space | Adapts to a new room with minimal data — 93% less than retraining from scratch |
 | **Memory preservation** | EWC++ regularization remembers what was learned during pretraining | Switching to a new task doesn't erase prior knowledge |
 | **Hard-negative mining** | Training focuses on the most confusing examples to learn faster | Better accuracy with the same amount of training data |
@@ -610,7 +590,7 @@ Verify the plugin structure: `bash plugins/ruview/scripts/smoke.sh`. Full detail
 | [User Guide](docs/user-guide.md) | Step-by-step guide: installation, first run, API usage, hardware setup, training |
 | [Build Guide](docs/build-guide.md) | Building from source (Rust and Python) |
 | [**Home Assistant + Matter Integration**](docs/integrations/home-assistant.md) | **Works with Home Assistant** via MQTT auto-discovery + **Works with Matter** (Apple Home / Google Home / Alexa / SmartThings) — full entity catalog, 3 starter blueprints, Lovelace dashboards, privacy mode, threshold tuning ([ADR-115](docs/adr/ADR-115-home-assistant-integration.md)). |
-| [**BFLD — Beamforming Feedback Layer for Detection**](v2/crates/wifi-densepose-bfld/README.md) | New privacy-gated WiFi sensing layer that measures + structurally prevents identity leakage from 802.11ac/ax Beamforming Feedback Information. Three type-enforced invariants (raw BFI never exits node, identity embedding is in-RAM-only, cross-site correlation cryptographically impossible via per-site BLAKE3 keyed hash + daily rotation). Ships full operator surface (`BfldPipeline`, `BfldPipelineHandle`, the Soul Signature §3.6 per-channel matcher `EnrolledMatcher`/`SoulMatchOracle` — experimental; named identity is data-gated, **measured** as not-separable on WiFi-only channels alone), MQTT topic router + HA-DISCO + availability + LWT, 3 operator HA blueprints, two runnable examples, eclipse-mosquitto:2 CI service container. 327+ tests. [ADR-118](docs/adr/ADR-118-bfld-beamforming-feedback-layer-for-detection.md) umbrella + sub-ADRs [119](docs/adr/ADR-119-bfld-frame-format-and-wire-protocol.md)/[120](docs/adr/ADR-120-bfld-privacy-class-and-hash-rotation.md)/[121](docs/adr/ADR-121-bfld-identity-risk-scoring.md)/[122](docs/adr/ADR-122-bfld-ruview-ha-matter-exposure.md)/[123](docs/adr/ADR-123-bfld-capture-path-nexmon-and-esp32.md). Research dossier: [`docs/research/BFLD/`](docs/research/BFLD/) (11 files, 13,544 words). |
+| [**BFLD — Beamforming Feedback Layer for Detection**](v2/crates/wifi-densepose-bfld/README.md) | New privacy-gated WiFi sensing layer that measures + structurally prevents identity leakage from 802.11ac/ax Beamforming Feedback Information. Three type-enforced invariants (raw BFI never exits node, identity embedding is in-RAM-only, cross-site correlation cryptographically impossible via per-site BLAKE3 keyed hash + daily rotation). Ships full operator surface (`BfldPipeline`, `BfldPipelineHandle`, Soul Signature `SoulMatchOracle` integration), MQTT topic router + HA-DISCO + availability + LWT, 3 operator HA blueprints, two runnable examples, eclipse-mosquitto:2 CI service container. 327+ tests. [ADR-118](docs/adr/ADR-118-bfld-beamforming-feedback-layer-for-detection.md) umbrella + sub-ADRs [119](docs/adr/ADR-119-bfld-frame-format-and-wire-protocol.md)/[120](docs/adr/ADR-120-bfld-privacy-class-and-hash-rotation.md)/[121](docs/adr/ADR-121-bfld-identity-risk-scoring.md)/[122](docs/adr/ADR-122-bfld-ruview-ha-matter-exposure.md)/[123](docs/adr/ADR-123-bfld-capture-path-nexmon-and-esp32.md). Research dossier: [`docs/research/BFLD/`](docs/research/BFLD/) (11 files, 13,544 words). |
 | [**SENSE-BRIDGE — rvagent MCP server**](tools/ruview-mcp/README.md) | Dual-transport MCP server (`@ruvnet/rvagent`) bridging the RuView sensing stack to AI agents (Claude Code, Cursor, ruflo swarms). 6 tools wired: `ruview.presence.now`, `ruview.vitals.get_{breathing,heart_rate,all}`, `ruview.bfld.last_scan`, `ruview.bfld.subscribe`. stdio + Streamable HTTP (`POST /mcp`, Origin-validated, bearer-token auth, `127.0.0.1` bind). Full 20-tool Zod schema barrel + 5 RUVIEW-POLICY governance tools. 93 tests. [ADR-124](docs/adr/ADR-124-rvagent-mcp-ruvector-npm-integration.md). Try: `npx @ruvnet/rvagent stdio`. |
 | [Semantic Primitives — Precision/Recall](docs/integrations/semantic-primitives-metrics.md) | Per-primitive F1 on the held-out paired-capture set: someone-sleeping, possible-distress, room-active, elderly-inactivity-anomaly, meeting, bathroom, fall-risk, bed-exit, no-movement, multi-room. |
 | [Claude Code / Codex Plugin](plugins/ruview/README.md) | The `ruview` plugin + marketplace — skills, `/ruview-*` commands, agents, and the Codex prompt mirror |
@@ -1,50 +0,0 @@
-# AetherArena ("AA") — The Official Spatial-Intelligence Benchmark
-
-> **Public leaderboard. Private evaluation split. Open scorer. Signed results.**
-
-AetherArena is a **standalone, project-agnostic benchmark** for camera-free **spatial intelligence** — pose, presence, occupancy, tracking, and vitals from RF/WiFi (and, over time, mmWave / UWB / radar / lidar / multimodal). It is **not** a single-vendor leaderboard: any team, framework, or sensing modality can enter, and every entrant — including the RuView baseline that donated the seed scorer — is scored by the identical, open, pinned harness.
-
-Specified in [ADR-149](../docs/adr/ADR-149-public-community-leaderboard-huggingface.md) (Accepted).
-
-Canonical home: **`ruvnet/aether-arena`** + a Hugging Face Space (deploy pending — see `STATUS`).
-
---
-
-## Why
-
-WiFi/RF spatial sensing has no shared yardstick — papers self-report against inconsistent splits and metrics, with **no accounting for latency, reproducibility, or privacy leakage**. AA fixes the *measurement*, not just the models: a single deterministic scorer, a private held-out split nobody can train on, and a signed result ledger that can't be silently edited.
-
-## What gets measured (v0)
-
-| Category | Metric | Status |
-|----------|--------|--------|
-| **Pose** | PCK@0.2 (all / torso), OKS | Ranked |
-| **Presence** | accuracy, FP/FN | Ranked |
-| **Edge latency** | p50 / p95 / p99 ms | Ranked |
-| **Determinism** | proof-hash pass/fail | Ranked (gate) |
-| Tracking (MOTA) | — | activates when multi-person clips land |
-| Vitals (BPM err) | — | activates when paired vitals ground truth lands |
-| **Privacy leakage** | membership-inference ∈ [0,1] | **gated — not ranked** until the attacker ships |
-| Cross-room | degradation ratio | coming soon |
-
-The headline rank is the **category metric**; an optional `arena_score = quality × latency_factor × privacy_factor × determinism_gate` is exposed alongside (never instead) so accuracy can't win at any cost. See ADR-149 §2.5.
-
-## How scoring works
-
-The scorer is RuView's **already-published** `wifi-densepose-train` acceptance harness (`ruview_metrics` + ADR-145 `ablation`), run in a pinned sandbox. **You submit a model, not predictions** — predictions on data you hold prove nothing. Your model is scored against a **private** MM-Fi held-out split (CC BY-NC 4.0; Wi-Pose excluded for redistribution reasons), and one **signed, append-only** row is written to the results ledger with a determinism proof hash.
-
-Submission lifecycle: `submitted → validated → quarantined → smoke_scored → full_scored → published` (or `rejected` with a reason). The model only ever runs inside a no-network, read-only-FS sandbox.
-
-## Submit (when the Space is live)
-
-1. Write a manifest: [`schema/aa-submission.toml`](schema/aa-submission.toml).
-2. Push your model artifact (`.safetensors` / `.rvf` / LoRA adapter) + manifest to the Space.
-3. Watch it move through the lifecycle; your signed row appears on the board.
-
-## Verify it's fair (you don't have to trust us)
-
-See [`VERIFY.md`](VERIFY.md) — run the **open scorer** locally on the **public smoke split**, reproduce the determinism hash, and confirm RuView's own entries were scored by the identical path. That five-step check is the launch gate (ADR-149 §7).
-
-## Neutrality
-
-AA is a neutral commons. The scorer is open and versioned; any metric change is a public `harness_version` bump that **re-scores all entries**. RuView donated the seed harness and enters as one baseline — it gets no special treatment (ADR-149 §2.8).
@@ -1,30 +0,0 @@
-# AetherArena — Build Status
-
-Tracks ADR-149 implementation milestones. "Complete" = benchmark **infrastructure** done,
-tested, CI-gated, deploy-ready, RuView baseline entered, §7 acceptance test passing.
-Model **SOTA** (e.g. MM-Fi PCK@20 ~72%) is a separate long-running ML effort, blocked on
-ADR-079 camera-ground-truth collection — *not* an infra-completion blocker.
-
-| # | Milestone | Status |
-|---|-----------|--------|
-| M1 | ADR-149 Accepted + committed | ✅ done |
-| M2 | Scorer runner (`aa_score_runner`) — **real model scoring** + witness (proof+inputs hash) + **repeatability analysis** | ✅ done — builds `--no-default-features`, determinism gate PASS, repeatable 16/16 |
-| M3 | CI harness-gate workflow (PR runs scorer + repeatability + real-scoring smoke + ledger verify) | ✅ done — `.github/workflows/aether-arena-harness.yml` |
-| M4 | Scaffold: README + submission schema + VERIFY (acceptance test) | ✅ done |
-| M5 | Public smoke split (committed) + private MM-Fi held-out split prep | 🟡 smoke split done (`fixtures/smoke_*.json`); private MM-Fi prep pending |
-| M6 | HF Space (Gradio) — leaderboard + ledger integrity + submit/verify/about | ✅ deployed → https://huggingface.co/spaces/ruvnet/aether-arena (sandboxed scorer container = later hardening) |
-| M7 | **Witness ledger chain** — append-only, hash-chained, tamper-evident | ✅ done — `ledger/ledger_tools.py` (seed/append/verify); tamper test fails as designed |
-| M8 | Public launch | ✅ Space **LIVE** (gradio 5.9.1, serving 200) — **board empty, awaiting first real harness score** (benchmark-first: no seeded numbers) |
-
-## v0 infrastructure: COMPLETE
-Implement ✅ · Test ✅ · Deploy to HF ✅ (https://huggingface.co/spaces/ruvnet/aether-arena) · Instructions+Verification ✅ · PR runs the harness ✅ (PR #874, AA harness gate **passed**).
-Remaining = data + hardening, not infra: private MM-Fi held-out split (M5), sandboxed scorer container (M6), privacy-leakage attacker (gated category), and **model SOTA** (separate ML effort, blocked on ADR-079 — explicitly not an infra exit).
-
-## Benchmark-first posture (per user direction)
- **No placeholder numbers on the board.** The ledger seeds to genesis only; every result is a real scoring-pipeline witness. RuView gets no seeded baseline.
- **Witness chain** = `inputs_sha256` (binds witness to exact inputs) + `proof_sha256` (cross-platform-stable score hash) + the append-only hash-chained ledger. Repeatability analysis (`--repeat N`) proves the proof hash is identical across runs.
-
-## Blockers / decisions needed
- **HF deploy (M6)** — token is in GCP Secret Manager (`HUGGINGFACE_API_KEY`); creating the public `ruvnet/aether-arena` Space still wants explicit go.
- **MM-Fi is CC BY-NC** → AA must stay non-commercial / legally distinct from the commercial RuView product.
- **Private MM-Fi split (M5)** — needs the dataset pulled + a held-out split assembled before real public scoring replaces the smoke fixture.
@@ -1,78 +0,0 @@
-# Verifying AetherArena (you don't have to trust us)
-
-AA's credibility rests on a stranger being able to reproduce a score and see that the rules are fair. This is the **launch gate** (ADR-149 §7): v0 does not ship until all five checks below pass for someone with no insider access.
-
-> **Wider context:** this page covers the *leaderboard scorer*. For the whole-platform answer to
-> "is this real / does it actually work?" — including the deterministic pipeline proof, the
-> published models + public-benchmark numbers, and the built-in-public development trail — see
-> [`docs/proof-of-capabilities.md`](../docs/proof-of-capabilities.md).
-
-## The open scorer
-
-The scoring engine is a pure-Rust, GPU-free binary: `aa_score_runner` in `wifi-densepose-train`. It runs the real `ruview_metrics` pose-acceptance harness on a fixed fixture and emits a cross-platform-stable SHA-256 **determinism proof**.
-
-### Reproduce the determinism hash locally
-
-```bash
-cd v2
-# Verify the committed expected hash still matches (this is the CI gate):
-cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features
-# → prints the witness (inputs_sha256 + proof_sha256) and "VERDICT: PASS"
-
-# See the witness row as JSON:
-cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --json
-```
-
-### Witness chain — proof + repeatability analysis
-
-Every score is a **witness**: `inputs_sha256` (binds it to the exact inputs scored)
-+ `proof_sha256` (cross-platform-stable hash of the quantised score) + `harness_version`.
-Witnesses are recorded in an **append-only, hash-chained ledger** (each row references
-the previous row's hash), so a silent edit to any past row breaks the chain.
-
-```bash
-# Repeatability: run the scorer K times, confirm ONE identical proof hash:
-cd v2
-cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --repeat 16
-# → {"repeatability":{"runs":16,"unique_proof_hashes":1,"repeatable":true,...}}
-
-# Real model scoring (score predictions against an eval split):
-cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- \
-  --split ../aether-arena/fixtures/smoke_split.json \
-  --pred  ../aether-arena/fixtures/smoke_pred.json --json
-
-# Verify the witness ledger chain is intact (tamper-evident):
-cd ../aether-arena/ledger && python3 ledger_tools.py verify
-# → "OK: N rows, chain intact"   (edit any row and it reports the broken link)
-```
-
-The expected hash is committed at [`fixtures/expected_score.sha256`](fixtures/expected_score.sha256). Same harness version + same fixture → same hash on glibc / MSVC / Apple. If your local run prints `VERDICT: PASS`, you have reproduced the scorer.
-
-### What happens if the scoring maths changes
-
-Any edit to `ruview_metrics.rs`, `ablation.rs`, or `aa_score_runner.rs` moves the hash and **fails the CI gate** (`.github/workflows/aether-arena-harness.yml`) until the maintainer regenerates and reviews:
-
-```bash
-cargo run -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --generate-hash \
-  > aether-arena/fixtures/expected_score.sha256
-```
-
-So a scorer change is always a reviewed, public diff — never silent. That's `harness_version` pinning + `determinism_gate` in action (ADR-149 §2.4–§2.5).
-
-## The five-step acceptance test (v0 launch gate)
-
-A stranger must be able to:
-
-1. **Submit** a model (artifact + `schema/aa-submission.toml`) with no insider help.
-2. **Get a deterministic score** — same model + same `harness_version` → same numbers.
-3. **See the signed row** appended to the public results ledger.
-4. **Rerun the scorer locally** on the public smoke split and reproduce the logic (the command above).
-5. **Understand why the rank is fair** — private split, open scorer, pinned version, proof hash — from these docs alone.
-
-If any step fails, v0 is not ready.
-
-## Current status
-
- ✅ Step 4 (rerun the open scorer locally, reproduce the hash) — **works today** via `aa_score_runner`.
- ✅ CI harness gate runs the scorer on every PR.
- ⏳ Steps 1–3, 5 (HF Space submission flow + signed ledger) — in progress; require the HF Space deploy (needs an HF token / maintainer authorization).
@@ -1,87 +0,0 @@
-# RuView Calibration Service (reference implementation)
-
-Turn a **shared WiFi-CSI pose base model** into a room-specific one with a **30-second labeled
-calibration** and a **~11 KB per-room LoRA adapter**. This is the deployable resolution of the
-cross-subject / cross-environment generalization problem (full study: [ADR-150 §3.3–3.6](../../docs/adr/ADR-150-rf-foundation-encoder.md)).
-
-## Why
-
-Zero-shot WiFi pose generalizes poorly to a **new room or new person** — an unseen room can drop a
-strong model to near-random. But that gap is **not** algorithmically closeable (CORAL, DANN,
-instance-norm, contrastive foundation-pretraining all failed) and **not** closeable by collecting
-more subjects (saturates ~64%). It **is** closeable, cheaply, at deployment time: a handful of
-labeled frames from the actual room pin down its multipath instantly.
-
-| Deployment case | Zero-shot | + in-room calibration |
-|-----------------|----------:|----------------------:|
-| Same room, new person (cross-subject) | 64% | **76%** (200 samples) |
-| **New room + new person (cross-environment)** | **~10%** | **60% @ 5 samples → 73% @ 200** |
-
-**Verified demo (this code, source-only base on an unseen MM-Fi room E04):**
-`zero-shot 3.09% → after 200-sample calibration 74.29%` (+71 pts).
-
-## How it works
-
-A frozen shared **base** (transformer + temporal attention pool + skeleton-graph head, the published
-[`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose)) plus a
-tiny **LoRA adapter** (rank 8 on the input projection + pose head — **11,200 params ≈ 11 KB int8 /
-22 KB fp16**) fitted per room. Thousands of room-adapters hang off one base.
-
-## Usage
-
-```bash
-# 1) Capture a short labeled clip in the deployment room -> calib.npz {X:[N,3,114,10], Y:[N,17,2]}
-#    (~100–200 samples recommended; below ~20 the adapter can underperform zero-shot)
-
-# 2) Fit the per-room adapter (~11 KB):
-python calibrate.py --base pose_mmfi_best.pt --data calib.npz --out room.adapter.npz
-
-# 3) Run calibrated inference (base + room adapter):
-python infer.py --base pose_mmfi_best.pt --adapter room.adapter.npz --data frames.npz --out kp.npy
-#    omit --adapter to run the uncalibrated (zero-shot) base
-```
-
-`X` is CSI amplitude `[N, 3 antennas, 114 subcarriers, 10 frames]` (per-sample standardization is
-applied internally). `Y` is `[N,17,2]` COCO keypoints in `[0,1]`.
-
-## Calibration budget (measured, rank-8 LoRA, 3 seeds — ADR-150 §3.5)
-
-| Labeled samples/room | cross-subject | cross-environment |
-|---------------------:|--------------:|------------------:|
-| 0 (zero-shot) | 64% | ~10% |
-| 5 | — | 60% |
-| 20 | 66% | 66% |
-| 50 | 70% | 70% |
-| 200 | 72% | 73% |
-
-Knee at ~50 samples (~70%); **below ~20 samples the adapter can hurt** (too few to fit reliably).
-
-## Two models, two producers (not interchangeable)
-
-Adapters are **model-specific**. There are two calibration producers here:
-
-| Producer | Target model | Input | Adapter format | Consumer |
-|----------|--------------|-------|----------------|----------|
-| `calibrate.py` | MM-Fi **transformer** (`pose_mmfi_best.pt`, 3×114×10) | `[N,3,114,10]` | `.npz` (`proj`/`head` LoRA) | this Python `infer.py` |
-| `cog_calibrate.py` | cog **conv+MLP** (`pose_v1.safetensors`, 56×20) | `[N,56,20]` | `.safetensors` (`fc1.a`/`fc1.b`/`fc2.a`/`fc2.b`) | Rust `cog-pose-estimation run --adapter` |
-
-```bash
-# Produce a cog-format per-room adapter for the deployed Rust pose engine:
-python cog_calibrate.py --base pose_v1.safetensors --data calib.npz --out room.safetensors
-# then in the cog runtime:
-cog-pose-estimation run --config <cfg> --adapter room.safetensors
-```
-
-Same LoRA *mechanism* (ADR-150 §3.5), different architecture and key layout — an adapter from one
-producer will not load into the other model.
-
-## Notes
-
- **Calibration only helps when the base hasn't already seen the room.** The published flagship was
-  trained on MM-Fi `random_split`, so calibrating it on an MM-Fi subject is a near-no-op (it already
-  saw them); for a genuinely new real-world room it is zero-shot and calibration applies. To
-  *reproduce the demo* on a held-out MM-Fi room, train a source-only base (exclude the target
-  environment) — see `ADR-150 §3.6` and the few-shot harness in `aether-arena/staging/`.
- Adapter is saved fp16 (~22 KB); quantize to int8 for the ~11 KB on-device form.
- Inference is real-time on CPU (the 75 K-param `micro` variant runs in 0.135 ms single-thread x86;
-  see [`docs/benchmarks/wifi-pose-efficiency-frontier.md`](../../docs/benchmarks/wifi-pose-efficiency-frontier.md)).
@@ -1,71 +0,0 @@
-"""RuView per-room calibration — fit a ~11 KB LoRA adapter from a short labeled in-room capture.
-
-    python calibrate.py --base pose_mmfi_best.pt --data room_calib.npz --out room_A.adapter.npz
-
-`room_calib.npz` must contain `X` [N,3,114,10] CSI amplitude and `Y` [N,17,2] (or [N,34]) keypoints
-in [0,1] — the labeled calibration samples from the deployment room (~100–200 recommended; ≥20).
-Outputs a tiny adapter (.npz, ~11 KB) that, loaded over the shared base at inference, recovers
-SOTA-level pose for that room/person (ADR-150 §3.5–3.6).
-"""
-import argparse
-import numpy as np
-import torch
-import torch.nn as nn
-
-from model import PoseNet, standardize
-
-
-def main():
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--base", required=True, help="base checkpoint (pose_mmfi_best.pt)")
-    ap.add_argument("--data", required=True, help="labeled calibration .npz with X and Y")
-    ap.add_argument("--out", required=True, help="output adapter .npz")
-    ap.add_argument("--rank", type=int, default=8)
-    ap.add_argument("--iters", type=int, default=600)
-    ap.add_argument("--lr", type=float, default=8e-4)
-    ap.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu")
-    a = ap.parse_args()
-
-    z = np.load(a.data)
-    X = torch.tensor(z["X"].astype(np.float32))
-    Y = torch.tensor(z["Y"].reshape(len(z["Y"]), 34).astype(np.float32))
-    n = len(X)
-    if n < 20:
-        print(f"WARNING: only {n} calibration samples — below ~20 the adapter may underperform "
-              f"zero-shot (ADR-150 §3.5). Recommend ~100–200.")
-    dev = a.device
-
-    net = PoseNet().to(dev)
-    net.load_state_dict(torch.load(a.base, map_location=dev), strict=False)
-    net.add_lora(r=a.rank).to(dev)
-    for k, p in net.named_parameters():
-        p.requires_grad = k.endswith(".A") or k.endswith(".B")
-    trainable = [p for p in net.parameters() if p.requires_grad]
-    n_tr = sum(p.numel() for p in trainable)
-
-    Xs = standardize(X.to(dev))
-    Yt = Y.to(dev)
-    opt = torch.optim.AdamW(trainable, lr=a.lr, weight_decay=0.0)
-    lossf = nn.SmoothL1Loss(beta=0.1)
-    bs = min(128, n)
-    net.train()
-    for it in range(a.iters):
-        bi = torch.randint(0, n, (bs,), device=dev)
-        xb = Xs[bi]
-        # light augmentation (subcarrier dropout + noise) — matches training-time regularization
-        m = (torch.rand(xb.shape[0], xb.shape[1], 1, 1, device=dev) > 0.15).float()
-        xb = xb * m + 0.03 * torch.randn_like(xb) * torch.rand(xb.shape[0], 1, 1, 1, device=dev)
-        opt.zero_grad()
-        lossf(net(xb), Yt[bi]).backward()
-        opt.step()
-
-    adapter = net.lora_state()
-    nbytes = sum(v.astype(np.float16).nbytes for v in adapter.values())
-    np.savez(a.out, **{k: v.astype(np.float16) for k, v in adapter.items()},
-             _meta=np.array([a.rank, n, n_tr], dtype=np.int64))
-    print(f"saved {a.out} | rank {a.rank} | {n_tr:,} params | ~{nbytes/1024:.1f} KB fp16 | "
-          f"from {n} labeled samples")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,120 +0,0 @@
-"""Per-room calibration producer for the cog-pose-estimation **conv+MLP** model
-(`pose_v1.safetensors`, 56 subcarriers x 20 frames). Companion to `calibrate.py`
-(which targets the MM-Fi *transformer* model) — different model, different adapter
-key layout, NOT interchangeable (ADR-150 §3.5).
-
-Fits a rank-r LoRA on the pose head (fc1, fc2) from a short labeled in-room capture and
-writes a **safetensors** adapter with keys `fc1.a`/`fc1.b`/`fc2.a`/`fc2.b` (scale baked
-into `b`) — exactly what `cog-pose-estimation run --adapter <file>` consumes.
-
-    python cog_calibrate.py --base pose_v1.safetensors --data calib.npz --out room.safetensors
-
-`calib.npz`: `X` [N,56,20] CSI window + `Y` [N,17,2] (or [N,34]) keypoints in [0,1].
-"""
-import argparse
-import numpy as np
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-class CogPose(nn.Module):
-    """Mirrors cog-pose-estimation's PoseNet (Candle) exactly — same safetensors keys."""
-
-    def __init__(self):
-        super().__init__()
-        self.enc = nn.ModuleDict({
-            "c1": nn.Conv1d(56, 64, 3, padding=1, dilation=1),
-            "c2": nn.Conv1d(64, 128, 3, padding=2, dilation=2),
-            "c3": nn.Conv1d(128, 128, 3, padding=4, dilation=4),
-        })
-        self.head = nn.ModuleDict({"fc1": nn.Linear(128, 256), "fc2": nn.Linear(256, 34)})
-        self.fc1_lora = None
-        self.fc2_lora = None
-
-    def _lora(self, slot, x, y):
-        if slot is None:
-            return y
-        a, b = slot
-        return y + (x @ a) @ b
-
-    def forward(self, x):                       # x: [B, 56, 20]
-        h = F.relu(self.enc["c1"](x))
-        h = F.relu(self.enc["c2"](h))
-        h = F.relu(self.enc["c3"](h))
-        h = h.mean(2)                            # [B, 128]
-        z1 = self.head["fc1"](h)
-        z1 = self._lora(self.fc1_lora, h, z1)
-        h1 = F.relu(z1)
-        z2 = self.head["fc2"](h1)
-        z2 = self._lora(self.fc2_lora, h1, z2)
-        return torch.sigmoid(z2)                 # [B, 34]
-
-    def add_lora(self, r=4):
-        self.fc1_lora = (nn.Parameter(torch.randn(128, r) * 0.02), nn.Parameter(torch.zeros(r, 256)))
-        self.fc2_lora = (nn.Parameter(torch.randn(256, r) * 0.02), nn.Parameter(torch.zeros(r, 34)))
-        for p in (*self.fc1_lora, *self.fc2_lora):
-            self.register_parameter(f"lora_{id(p)}", p)
-        return self
-
-
-def load_base(net: CogPose, path: str):
-    from safetensors.torch import load_file
-    sd = load_file(path)
-    # remap "enc.c1.weight" -> module dict keys
-    mapped = {}
-    for k, v in sd.items():
-        mapped[k.replace("enc.", "enc.").replace("head.", "head.")] = v
-    net.load_state_dict(mapped, strict=False)
-    return net
-
-
-def fit(base: str, data: str, out: str, rank: int = 4, iters: int = 400, lr: float = 1e-3):
-    z = np.load(data)
-    X = torch.tensor(z["X"].astype(np.float32))          # [N,56,20]
-    Y = torch.tensor(z["Y"].reshape(len(z["Y"]), 34).astype(np.float32))
-    n = len(X)
-    net = CogPose()
-    load_base(net, base)
-    net.add_lora(rank)
-    for p in net.parameters():
-        p.requires_grad = False
-    lora = [*net.fc1_lora, *net.fc2_lora]
-    for p in lora:
-        p.requires_grad = True
-    opt = torch.optim.AdamW(lora, lr=lr, weight_decay=0.0)
-    lossf = nn.SmoothL1Loss(beta=0.1)
-    bs = min(64, n)
-    net.train()
-    for _ in range(iters):
-        bi = torch.randint(0, n, (bs,))
-        opt.zero_grad()
-        lossf(net(X[bi]), Y[bi]).backward()
-        opt.step()
-
-    alpha = 16.0
-    scale = alpha / rank
-    a1, b1 = net.fc1_lora
-    a2, b2 = net.fc2_lora
-    tensors = {
-        "fc1.a": a1.detach().contiguous(),
-        "fc1.b": (b1.detach() * scale).contiguous(),    # bake scale into b
-        "fc2.a": a2.detach().contiguous(),
-        "fc2.b": (b2.detach() * scale).contiguous(),
-    }
-    from safetensors.torch import save_file
-    save_file(tensors, out)
-    return out, sum(p.numel() for p in lora), n
-
-
-if __name__ == "__main__":
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--base", required=True)
-    ap.add_argument("--data", required=True)
-    ap.add_argument("--out", required=True)
-    ap.add_argument("--rank", type=int, default=4)
-    ap.add_argument("--iters", type=int, default=400)
-    a = ap.parse_args()
-    out, np_, n = fit(a.base, a.data, a.out, a.rank, a.iters)
-    print(f"saved {out} | {np_} LoRA params from {n} samples "
-          f"(keys fc1.a/fc1.b/fc2.a/fc2.b — load with cog-pose-estimation run --adapter)")
@@ -1,49 +0,0 @@
-"""Run calibrated WiFi-CSI pose inference: shared base + a per-room LoRA adapter.
-
-    python infer.py --base pose_mmfi_best.pt --adapter room_A.adapter.npz --data frames.npz
-
-`frames.npz` contains `X` [N,3,114,10] CSI amplitude. Prints/saves [N,17,2] keypoints in [0,1].
-Omit --adapter to run the uncalibrated (zero-shot) base. With a room adapter, expect SOTA-level
-accuracy in that room/person; without one, zero-shot degrades in unseen rooms (ADR-150 §3.6).
-"""
-import argparse
-import numpy as np
-import torch
-
-from model import PoseNet, standardize
-
-
-def main():
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--base", required=True)
-    ap.add_argument("--adapter", default=None, help="per-room .adapter.npz (omit for zero-shot)")
-    ap.add_argument("--data", required=True, help=".npz with X [N,3,114,10]")
-    ap.add_argument("--out", default=None, help="optional .npy to save [N,17,2] keypoints")
-    ap.add_argument("--rank", type=int, default=8)
-    ap.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu")
-    a = ap.parse_args()
-    dev = a.device
-
-    net = PoseNet().to(dev)
-    net.load_state_dict(torch.load(a.base, map_location=dev), strict=False)
-    if a.adapter:
-        net.add_lora(r=a.rank).to(dev)
-        z = np.load(a.adapter)
-        net.load_lora({k: z[k].astype(np.float32) for k in z.files if k.endswith(".A") or k.endswith(".B")})
-    net.eval()
-
-    X = torch.tensor(np.load(a.data)["X"].astype(np.float32)).to(dev)
-    Xs = standardize(X)
-    out = []
-    with torch.no_grad():
-        for i in range(0, len(Xs), 4096):
-            out.append(net(Xs[i:i + 4096]).cpu().numpy())
-    kp = np.concatenate(out).reshape(-1, 17, 2)
-    print(f"inferred {len(kp)} frames | adapter={'yes' if a.adapter else 'NONE (zero-shot)'}")
-    if a.out:
-        np.save(a.out, kp)
-        print(f"saved keypoints -> {a.out}")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,107 +0,0 @@
-"""WiFi-CSI pose model + LoRA adapter for the RuView calibration service.
-
-Architecture matches the published flagship checkpoint
-[`ruvnet/wifi-densepose-mmfi-pose`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose)
-(`pose_mmfi_best.pt`): transformer encoder + temporal attention pooling + skeleton-graph head.
-
-The calibration service freezes this base and fits a tiny per-room **LoRA adapter** (rank 8 on the
-input projection + pose head ≈ 11 KB) from ~100–200 labeled in-room samples. Empirically that lifts
-cross-subject 64→72% and cross-environment 11→73% (ADR-150 §3.3–3.6).
-"""
-import numpy as np
-import torch
-import torch.nn as nn
-
-# COCO-17 skeleton edges for the graph-refinement head.
-EDGES = [(0, 1), (0, 2), (1, 3), (2, 4), (5, 6), (5, 7), (7, 9), (6, 8), (8, 10),
-         (5, 11), (6, 12), (11, 12), (11, 13), (13, 15), (12, 14), (14, 16)]
-_A = np.eye(17, dtype=np.float32)
-for _i, _j in EDGES:
-    _A[_i, _j] = _A[_j, _i] = 1.0
-_A = _A / _A.sum(1, keepdims=True)
-
-
-class LoRA(nn.Module):
-    """Low-rank adapter wrapping a frozen Linear: y = W·x + (x·A·B)·(alpha/r)."""
-
-    def __init__(self, base: nn.Linear, r: int = 8, alpha: int = 16):
-        super().__init__()
-        self.base = base
-        for p in self.base.parameters():
-            p.requires_grad = False
-        self.A = nn.Parameter(torch.zeros(base.in_features, r))
-        self.B = nn.Parameter(torch.zeros(r, base.out_features))
-        nn.init.normal_(self.A, std=0.02)
-        self.scale = alpha / r
-
-    def forward(self, x):
-        return self.base(x) + (x @ self.A @ self.B) * self.scale
-
-
-class GR(nn.Module):
-    """Skeleton-graph refinement: nudges joints toward anatomically consistent positions."""
-
-    def __init__(self, d=256, h=96):
-        super().__init__()
-        self.je = nn.Parameter(torch.randn(17, 32) * 0.02)
-        self.inp = nn.Linear(d + 34, h)
-        self.g1 = nn.Linear(h, h)
-        self.g2 = nn.Linear(h, h)
-        self.out = nn.Linear(h, 2)
-        self.register_buffer("A", torch.tensor(_A))
-
-    def forward(self, z, kp0):
-        B = z.shape[0]
-        f = torch.relu(self.inp(torch.cat(
-            [z.unsqueeze(1).expand(-1, 17, -1), self.je.unsqueeze(0).expand(B, -1, -1), kp0], -1)))
-        f = torch.relu(self.g1(torch.einsum('ij,bjh->bih', self.A, f)))
-        f = torch.relu(self.g2(torch.einsum('ij,bjh->bih', self.A, f)))
-        return kp0 + 0.3 * torch.tanh(self.out(f))
-
-
-class PoseNet(nn.Module):
-    """Flagship pose model. Input [B,3,114,10] CSI amplitude (per-sample standardized) -> [B,34]."""
-
-    def __init__(self, na=3, nsc=114, nt=10, d=256, L=4, H=8):
-        super().__init__()
-        self.proj = nn.Linear(na * nsc, d)
-        self.pos = nn.Parameter(torch.randn(1, nt, d) * 0.02)
-        enc = nn.TransformerEncoderLayer(d, H, d * 2, dropout=0.2, batch_first=True, activation='gelu')
-        self.tf = nn.TransformerEncoder(enc, L)
-        self.att = nn.Linear(d, 1)
-        self.head = nn.Sequential(nn.Linear(d, 256), nn.GELU(), nn.Dropout(0.3), nn.Linear(256, 34))
-        self.gr = GR(d)
-        self.na, self.nsc, self.nt = na, nsc, nt
-
-    def forward(self, x):
-        B = x.shape[0]
-        t = x.permute(0, 3, 1, 2).reshape(B, self.nt, self.na * self.nsc)
-        h = self.tf(self.proj(t) + self.pos)
-        w = torch.softmax(self.att(h), 1)
-        z = (h * w).sum(1)
-        kp0 = torch.sigmoid(self.head(z)).reshape(B, 17, 2)
-        return self.gr(z, kp0).reshape(B, 34)
-
-    def add_lora(self, r=8, alpha=16):
-        """Wrap the input projection + pose head with LoRA adapters (the ~11 KB calibration set)."""
-        self.proj = LoRA(self.proj, r, alpha)
-        self.head[0] = LoRA(self.head[0], r, alpha)
-        self.head[3] = LoRA(self.head[3], r, alpha)
-        return self
-
-    def lora_state(self) -> dict:
-        """Extract just the LoRA A/B tensors (the per-room adapter to save)."""
-        return {k: v.detach().cpu().numpy() for k, v in self.state_dict().items()
-                if k.endswith(".A") or k.endswith(".B")}
-
-    def load_lora(self, adapter: dict):
-        sd = self.state_dict()
-        for k, v in adapter.items():
-            sd[k] = torch.tensor(v)
-        self.load_state_dict(sd)
-        return self
-
-
-def standardize(x: torch.Tensor) -> torch.Tensor:
-    """Per-sample standardization used in training/inference."""
-    return (x - x.mean((1, 2, 3), keepdim=True)) / (x.std((1, 2, 3), keepdim=True) + 1e-6)
@@ -1,103 +0,0 @@
-"""Self-contained regression test for the RuView calibration service.
-
-Exercises the committed CLI end-to-end on synthetic data (CPU, no GPU, no real checkpoint):
-  build a base -> calibrate.py fits an adapter -> infer.py runs base+adapter -> assert the
-  adapter is small, inference is shape-correct and finite, and the adapter actually changes output.
-
-Run:  python test_calibration.py    (or via pytest)
-"""
-import json
-import subprocess
-import sys
-import tempfile
-from pathlib import Path
-
-import numpy as np
-import torch
-
-HERE = Path(__file__).parent
-sys.path.insert(0, str(HERE))
-from model import PoseNet, standardize  # noqa: E402
-
-
-def _make_base(path: Path):
-    torch.manual_seed(0)
-    net = PoseNet()
-    # Save without the deterministic gr.A buffer (mirrors the published checkpoint;
-    # calibrate.py/infer.py load with strict=False).
-    sd = {k: v for k, v in net.state_dict().items() if k != "gr.A"}
-    torch.save(sd, path)
-
-
-def _make_data(path: Path, n: int, seed: int):
-    rng = np.random.default_rng(seed)
-    X = rng.standard_normal((n, 3, 114, 10)).astype(np.float32)
-    Y = rng.random((n, 17, 2)).astype(np.float32)  # keypoints in [0,1]
-    np.savez(path, X=X, Y=Y)
-
-
-def _run(*args):
-    r = subprocess.run(
-        [sys.executable, str(HERE / args[0]), *map(str, args[1:])],
-        capture_output=True, text=True,
-    )
-    assert r.returncode == 0, f"{args[0]} failed:\n{r.stdout}\n{r.stderr}"
-    return r.stdout
-
-
-def test_calibration_end_to_end():
-    with tempfile.TemporaryDirectory() as d:
-        d = Path(d)
-        base = d / "base.pt"
-        calib = d / "calib.npz"
-        frames = d / "frames.npz"
-        adapter = d / "room.adapter.npz"
-        kp = d / "kp.npy"
-
-        _make_base(base)
-        _make_data(calib, n=40, seed=1)     # ≥20 → no underfit warning
-        _make_data(frames, n=16, seed=2)
-
-        # 1) calibrate -> adapter
-        out = _run("calibrate.py", "--base", base, "--data", calib, "--out", adapter,
-                   "--iters", "50", "--device", "cpu")
-        assert adapter.exists(), "adapter not written"
-        assert "saved" in out.lower()
-        sz = adapter.stat().st_size
-        assert sz < 200_000, f"adapter unexpectedly large ({sz} bytes)"
-
-        # adapter contains the expected LoRA tensors (materialize + close so the
-        # Windows tempdir can be cleaned up — np.load keeps a lazy file handle).
-        with np.load(adapter) as z:
-            keys = [k for k in z.files if k.endswith(".A") or k.endswith(".B")]
-            assert keys, f"adapter has no LoRA tensors: {z.files}"
-            lora = {k: z[k].astype(np.float32) for k in keys}
-
-        # 2) infer with adapter -> keypoints
-        _run("infer.py", "--base", base, "--adapter", adapter, "--data", frames,
-             "--out", kp, "--device", "cpu")
-        out_kp = np.load(kp)
-        assert out_kp.shape == (16, 17, 2), f"bad keypoint shape {out_kp.shape}"
-        assert np.isfinite(out_kp).all(), "non-finite keypoints"
-        assert (out_kp >= 0).all() and (out_kp <= 1).all(), "keypoints out of [0,1]"
-
-        # 3) adapter must actually change the output vs the zero-shot base
-        with np.load(frames) as fz:
-            frames_x = fz["X"][:]
-        net = PoseNet()
-        net.load_state_dict(torch.load(base, map_location="cpu"), strict=False)
-        net.eval()
-        x = standardize(torch.tensor(frames_x))
-        with torch.no_grad():
-            base_kp = net(x).reshape(16, 17, 2).numpy()
-        net.add_lora()
-        net.load_lora(lora)
-        net.eval()
-        with torch.no_grad():
-            cal_kp = net(x).reshape(16, 17, 2).numpy()
-        assert np.abs(base_kp - cal_kp).sum() > 1e-4, "adapter did not change output"
-
-
-if __name__ == "__main__":
-    test_calibration_end_to_end()
-    print("PASS: calibration service end-to-end (calibrate -> adapter -> infer)")
@@ -1,75 +0,0 @@
-"""Regression test for the cog-pose adapter producer (cog_calibrate.py).
-
-Uses the in-repo `pose_v1.safetensors` (skips if absent). Verifies the produced adapter:
-  - has the exact keys/shapes the Rust `cog-pose-estimation --adapter` loader expects,
-  - reduces calibration fit error,
-  - actually changes inference output,
-  - is tiny.
-Run: python test_cog_calibration.py   (or via pytest)
-"""
-import os
-import sys
-import tempfile
-from pathlib import Path
-
-import numpy as np
-import torch
-import torch.nn.functional as F
-
-HERE = Path(__file__).parent
-sys.path.insert(0, str(HERE))
-import cog_calibrate as C  # noqa: E402
-
-BASE = HERE / "../../v2/crates/cog-pose-estimation/cog/artifacts/pose_v1.safetensors"
-
-
-def test_cog_adapter_producer():
-    if not BASE.exists():
-        print(f"(skip — {BASE} not present)")
-        return
-    from safetensors.torch import load_file
-
-    rng = np.random.default_rng(0)
-    n = 120
-    X = rng.standard_normal((n, 56, 20)).astype("float32")
-    Y = (0.5 + 0.1 * X[:, :34, 0].reshape(n, 34)).clip(0, 1).astype("float32")
-
-    with tempfile.TemporaryDirectory() as d:
-        calib = os.path.join(d, "calib.npz")
-        adapter = os.path.join(d, "room.safetensors")
-        np.savez(calib, X=X, Y=Y)
-
-        net0 = C.CogPose()
-        C.load_base(net0, str(BASE))
-        net0.eval()
-        with torch.no_grad():
-            base_err = F.smooth_l1_loss(net0(torch.tensor(X)), torch.tensor(Y)).item()
-
-        _, nparam, _ = C.fit(str(BASE), calib, adapter, rank=4, iters=400)
-        t = load_file(adapter)
-
-        # exact Rust loader contract: a:[in,r], b:[r,out]
-        assert tuple(t["fc1.a"].shape) == (128, 4)
-        assert tuple(t["fc1.b"].shape) == (4, 256)
-        assert tuple(t["fc2.a"].shape) == (256, 4)
-        assert tuple(t["fc2.b"].shape) == (4, 34)
-
-        net = C.CogPose()
-        C.load_base(net, str(BASE))
-        net.add_lora(4)
-        with torch.no_grad():
-            net.fc1_lora[0].copy_(t["fc1.a"]); net.fc1_lora[1].copy_(t["fc1.b"] / (16 / 4))
-            net.fc2_lora[0].copy_(t["fc2.a"]); net.fc2_lora[1].copy_(t["fc2.b"] / (16 / 4))
-        net.eval()
-        with torch.no_grad():
-            cal_err = F.smooth_l1_loss(net(torch.tensor(X)), torch.tensor(Y)).item()
-            changed = (net0(torch.tensor(X[:8])) - net(torch.tensor(X[:8]))).abs().sum().item()
-
-        assert cal_err < base_err, f"calibration did not reduce error ({base_err} -> {cal_err})"
-        assert changed > 1e-3, "adapter inert"
-        assert nparam < 5000, f"adapter unexpectedly large ({nparam} params)"
-
-
-if __name__ == "__main__":
-    test_cog_adapter_producer()
-    print("PASS: cog adapter producer (Rust-loadable format, reduces error, active)")
@@ -1 +0,0 @@
-9c35e541d51f00998691b98948887ebca09b907d8eb29a113f97e792340456ba
@@ -1 +0,0 @@
-{"frames": [{"pred": [[0.4003, 0.2734], [0.5038, 0.4197], [0.2053, 0.4438], [0.4397, 0.685], [0.5796, 0.7645], [0.8001, 0.2195], [0.2789, 0.2833], [0.314, 0.5439], [0.511, 0.2259], [0.6008, 0.46], [0.4837, 0.3879], [0.3475, 0.5597], [0.6569, 0.3575], [0.437, 0.6539], [0.2341, 0.6038], [0.7331, 0.392], [0.5615, 0.4915]]}, {"pred": [[0.4669, 0.6066], [0.6012, 0.7873], [0.4124, 0.5997], [0.2832, 0.281], [0.2732, 0.3635], [0.2503, 0.4848], [0.6827, 0.715], [0.4336, 0.7165], [0.295, 0.3386], [0.5337, 0.3544], [0.4397, 0.5474], [0.5163, 0.5528], [0.7547, 0.6799], [0.4195, 0.4448], [0.2257, 0.2269], [0.384, 0.2176], [0.2419, 0.4332]]}, {"pred": [[0.5585, 0.283], [0.4325, 0.2934], [0.463, 0.4744], [0.4188, 0.3454], [0.215, 0.7565], [0.527, 0.2353], [0.7084, 0.6124], [0.3015, 0.6744], [0.4103, 0.3532], [0.7243, 0.6932], [0.3302, 0.4918], [0.2072, 0.3754], [0.7914, 0.4878], [0.7618, 0.4079], [0.323, 0.3386], [0.7104, 0.4997], [0.2673, 0.6077]]}, {"pred": [[0.6372, 0.4984], [0.4184, 0.6763], [0.4498, 0.7549], [0.2924, 0.303], [0.3069, 0.7022], [0.3954, 0.5098], [0.7836, 0.6071], [0.4733, 0.7114], [0.3407, 0.3793], [0.3408, 0.4678], [0.4156, 0.4911], [0.4525, 0.7519], [0.5117, 0.1985], [0.1893, 0.6784], [0.6281, 0.5346], [0.5175, 0.673], [0.36, 0.3665]]}, {"pred": [[0.5535, 0.6537], [0.568, 0.511], [0.4705, 0.5377], [0.6372, 0.7163], [0.5493, 0.7515], [0.2559, 0.4549], [0.2553, 0.6176], [0.2991, 0.6154], [0.7185, 0.7986], [0.4586, 0.5057], [0.2975, 0.4525], [0.3263, 0.3719], [0.5131, 0.4576], [0.557, 0.5268], [0.6572, 0.7736], [0.2146, 0.6526], [0.4662, 0.7371]]}, {"pred": [[0.2924, 0.7595], [0.2612, 0.2315], [0.2488, 0.7751], [0.2329, 0.7282], [0.4744, 0.4206], [0.3618, 0.267], [0.2477, 0.285], [0.3976, 0.3746], [0.494, 0.2874], [0.3596, 0.2112], [0.3311, 0.4692], [0.6912, 0.4727], [0.4434, 0.5233], [0.4139, 0.7048], [0.425, 0.3937], [0.2326, 0.631], [0.2655, 0.7116]]}, {"pred": [[0.3609, 0.3437], [0.285, 0.486], [0.7734, 0.5468], [0.3657, 0.4093], [0.4728, 0.5019], [0.1866, 0.3545], [0.2172, 0.2028], [0.5613, 0.5238], [0.6252, 0.7205], [0.7998, 0.2954], [0.242, 0.7063], [0.6259, 0.6883], [0.5148, 0.7141], [0.5577, 0.7434], [0.3233, 0.2131], [0.2652, 0.7066], [0.5753, 0.5885]]}, {"pred": [[0.6787, 0.6504], [0.6051, 0.2297], [0.2539, 0.3475], [0.6437, 0.7807], [0.4981, 0.6149], [0.5716, 0.2367], [0.6486, 0.3632], [0.2433, 0.369], [0.6061, 0.3731], [0.4955, 0.2591], [0.7676, 0.7602], [0.6899, 0.7716], [0.3143, 0.7707], [0.3031, 0.4997], [0.7076, 0.5133], [0.3382, 0.7196], [0.2002, 0.4871]]}]}
@@ -1 +0,0 @@
-{"frames": [{"gt": [[0.3943, 0.2905], [0.5215, 0.4194], [0.2225, 0.4602], [0.4547, 0.6961], [0.5765, 0.7686], [0.7858, 0.2279], [0.2866, 0.2707], [0.3084, 0.549], [0.5286, 0.2377], [0.6082, 0.4566], [0.4719, 0.3799], [0.3465, 0.5447], [0.6377, 0.3728], [0.4509, 0.6543], [0.2235, 0.6009], [0.7253, 0.3882], [0.5479, 0.4737]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.4845, 0.5985], [0.5883, 0.7959], [0.4315, 0.6012], [0.3008, 0.2703], [0.2776, 0.3486], [0.2483, 0.4695], [0.6916, 0.7184], [0.4153, 0.7305], [0.3057, 0.3392], [0.5535, 0.3576], [0.4216, 0.5398], [0.5093, 0.5706], [0.7397, 0.668], [0.4354, 0.4394], [0.2373, 0.2404], [0.404, 0.2315], [0.2609, 0.4182]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.5684, 0.2891], [0.4185, 0.2737], [0.4796, 0.4903], [0.4056, 0.3589], [0.2139, 0.7706], [0.5259, 0.2162], [0.718, 0.6177], [0.3002, 0.6632], [0.3978, 0.3338], [0.7116, 0.6836], [0.336, 0.5106], [0.2168, 0.3677], [0.7739, 0.4683], [0.773, 0.4188], [0.318, 0.3226], [0.7043, 0.4877], [0.2509, 0.5964]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.6501, 0.4868], [0.3995, 0.6805], [0.4408, 0.7681], [0.2762, 0.2907], [0.2877, 0.6959], [0.4102, 0.5292], [0.7825, 0.5898], [0.4603, 0.723], [0.3511, 0.3758], [0.3556, 0.4514], [0.4123, 0.4749], [0.4524, 0.7506], [0.5141, 0.2112], [0.2024, 0.6795], [0.6351, 0.5339], [0.5333, 0.6706], [0.3491, 0.3662]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.537, 0.656], [0.5675, 0.5033], [0.4714, 0.52], [0.6195, 0.7259], [0.5357, 0.766], [0.273, 0.4653], [0.2439, 0.6017], [0.2927, 0.6297], [0.7297, 0.7805], [0.439, 0.4924], [0.2969, 0.4589], [0.3174, 0.3911], [0.5324, 0.4643], [0.5744, 0.5074], [0.673, 0.783], [0.2238, 0.6674], [0.4534, 0.7468]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.2896, 0.7515], [0.2537, 0.2345], [0.2434, 0.763], [0.2502, 0.7137], [0.4723, 0.4035], [0.3607, 0.2775], [0.2657, 0.2969], [0.3872, 0.383], [0.5001, 0.3067], [0.3503, 0.2092], [0.3137, 0.4849], [0.6914, 0.4593], [0.4359, 0.504], [0.4056, 0.6994], [0.4428, 0.4085], [0.2424, 0.6445], [0.2507, 0.7048]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.3692, 0.3453], [0.2945, 0.4675], [0.7836, 0.5282], [0.3857, 0.414], [0.4848, 0.5017], [0.203, 0.3585], [0.225, 0.2135], [0.5513, 0.5175], [0.6296, 0.7275], [0.7908, 0.2897], [0.2263, 0.7012], [0.6403, 0.6873], [0.5026, 0.701], [0.5504, 0.7357], [0.338, 0.2187], [0.2629, 0.7015], [0.5757, 0.6084]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.6786, 0.649], [0.5956, 0.2396], [0.2447, 0.3593], [0.6439, 0.7854], [0.4874, 0.6102], [0.5857, 0.2465], [0.6459, 0.3827], [0.2364, 0.3613], [0.6054, 0.3745], [0.4798, 0.2711], [0.7869, 0.7618], [0.6919, 0.7809], [0.3259, 0.7674], [0.285, 0.5144], [0.6921, 0.5052], [0.3388, 0.7386], [0.2022, 0.495]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}]}
@@ -1,5 +0,0 @@
-{"benchmark": "AetherArena", "created": "2026-05-30", "kind": "genesis", "note": "Official Spatial-Intelligence Benchmark \u2014 append-only signed ledger. Entries are real harness scores only; no seeded numbers.", "prev_hash": "0000000000000000000000000000000000000000000000000000000000000000", "row_hash": "940bdc6f0f5dd00f4d89e13a8fa843bab3c9ddf1b8051f426a1701e730249231", "seq": 0, "spec": "ADR-149"}
-{"abs_gain": "+9.38", "benchmark": "MM-Fi", "category": "pose", "caveat": "Protocol-matched MM-Fi random_split result; NOT solved real-world generalization. Random split has temporal/subject-adjacency effects common to this benchmark family. Leakage-free cross-subject is far lower (~11-27%) and is the real deployment frontier.", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20 (||right_shoulder-left_hip|| norm, 17 COCO kpts)", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer (4L/8H ~2M params, temporal-attention)", "prev_hash": "940bdc6f0f5dd00f4d89e13a8fa843bab3c9ddf1b8051f426a1701e730249231", "protocol": "random_split (ratio=0.8, seed=0)", "rel_gain": "+13.0%", "reproduce": "download MM-Fi -> parse_mmfi_zips.py -> train_tf_torso.py X.npy Y.npy split_random.npy (seed 0)", "row_hash": "76598d8e1320d5248f8cd854a8ffa22a99bd2a2f0e0e7f2d2b1df79af16001d5", "score_pct": 81.63, "scored_at": "2026-05-30", "seq": 1, "sota_ref": "MultiFormer 72.25 (CSI2Pose 68.41)", "submitter": "ruvnet", "tier": "Gold"}
-{"abs_gain": "+11.34", "benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer + skeleton-graph head + 3-ensemble + TTA", "note": "Best in-domain. Stacks attention-pooling + transformer + skeleton-graph refine + warmup + TTA + 3-model ensemble. Supersedes the 81.63 single-model entry.", "prev_hash": "76598d8e1320d5248f8cd854a8ffa22a99bd2a2f0e0e7f2d2b1df79af16001d5", "protocol": "random_split (0.8, seed 0)", "row_hash": "5780a4bc3e98eb0e30c1ecfa9091e57b280444fa1f21cd5146797e408580e4ab", "score_pct": 83.59, "scored_at": "2026-05-30", "seq": 2, "sota_ref": "MultiFormer 72.25 (CSI2Pose 68.41)", "submitter": "ruvnet", "tier": "Gold"}
-{"benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer", "note": "Leakage-free generalization to unseen people, shared rooms. Honest deployment-relevant number.", "prev_hash": "5780a4bc3e98eb0e30c1ecfa9091e57b280444fa1f21cd5146797e408580e4ab", "protocol": "cross_subject (official, val=S05,S10,..,S40)", "row_hash": "d989e4e1dbc0182610305fdfbde8b094413b87c913283a46bf41f4afba7a06fd", "score_pct": 64.04, "scored_at": "2026-05-30", "seq": 3, "sota_ref": "(no matched public ref)", "submitter": "ruvnet", "tier": "Silver"}
-{"benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer + CORAL domain alignment", "note": "The real deployment frontier (new room). CORAL transductive DG (+30% rel over control). Data-bound: MM-Fi has only 3 source rooms.", "prev_hash": "d989e4e1dbc0182610305fdfbde8b094413b87c913283a46bf41f4afba7a06fd", "protocol": "cross_environment (train E01-03 -> test E04, new room)", "row_hash": "bf370487bde88e198c13877956dab3c83766a6a24afef0b78b6ac7aa130bb207", "score_pct": 17.51, "scored_at": "2026-05-30", "seq": 4, "sota_ref": "(hard frontier; control 13.52)", "submitter": "ruvnet", "tier": "Bronze"}
@@ -1,100 +0,0 @@
-#!/usr/bin/env python3
-"""AetherArena append-only, tamper-evident results ledger (ADR-149 §2.3/§2.4).
-
-Each row is hash-chained to the previous one: ``row_hash = sha256(canonical_row
-+ prev_hash)``. Any silent edit to an earlier row breaks every subsequent
-``prev_hash`` link, so the ledger is append-only and verifiable by anyone — no
-trust in the maintainer required. (Ed25519 row signing is the next hardening;
-the chain already makes tampering detectable.)
-
-Usage:
-    python ledger_tools.py seed        # (re)build ledger.jsonl with genesis + baseline
-    python ledger_tools.py verify      # verify the whole chain  -> exit 0 / 1
-    python ledger_tools.py append '<json-row>'   # append one scored row
-"""
-import hashlib
-import json
-import sys
-from pathlib import Path
-
-LEDGER = Path(__file__).parent / "ledger.jsonl"
-GENESIS_PREV = "0" * 64
-
-
-def canonical(row: dict) -> bytes:
-    # Stable key order, no whitespace -> deterministic bytes for hashing.
-    body = {k: row[k] for k in sorted(row) if k != "row_hash"}
-    return json.dumps(body, separators=(",", ":"), sort_keys=True).encode()
-
-
-def row_hash(row: dict) -> str:
-    return hashlib.sha256(canonical(row)).hexdigest()
-
-
-def read_rows() -> list[dict]:
-    if not LEDGER.exists():
-        return []
-    return [json.loads(l) for l in LEDGER.read_text().splitlines() if l.strip()]
-
-
-def append(entry: dict) -> dict:
-    rows = read_rows()
-    prev = rows[-1]["row_hash"] if rows else GENESIS_PREV
-    entry = dict(entry)
-    entry["seq"] = len(rows)
-    entry["prev_hash"] = prev
-    entry["row_hash"] = row_hash(entry)
-    with LEDGER.open("a") as f:
-        f.write(json.dumps(entry, sort_keys=True) + "\n")
-    return entry
-
-
-def verify() -> bool:
-    rows = read_rows()
-    prev = GENESIS_PREV
-    for i, r in enumerate(rows):
-        if r.get("seq") != i:
-            print(f"FAIL: row {i} seq mismatch ({r.get('seq')})")
-            return False
-        if r.get("prev_hash") != prev:
-            print(f"FAIL: row {i} prev_hash broken — ledger was edited")
-            return False
-        if r.get("row_hash") != row_hash(r):
-            print(f"FAIL: row {i} row_hash mismatch — row was tampered")
-            return False
-        prev = r["row_hash"]
-    print(f"OK: {len(rows)} rows, chain intact")
-    return True
-
-
-def seed():
-    """Rebuild with the genesis row only — an EMPTY board.
-
-    Benchmark-first: no placeholder/hand-entered numbers ever sit on the
-    leaderboard. Every result row is produced by the real scoring pipeline
-    (load model -> run inference -> score against the private eval split ->
-    proof hash). The board starts empty and awaits the first real harness score,
-    including RuView's own — which gets no special seeding.
-    """
-    if LEDGER.exists():
-        LEDGER.unlink()
-    append({
-        "kind": "genesis",
-        "benchmark": "AetherArena",
-        "spec": "ADR-149",
-        "note": "Official Spatial-Intelligence Benchmark — append-only signed ledger. "
-                "Entries are real harness scores only; no seeded numbers.",
-        "created": "2026-05-30",
-    })
-
-
-if __name__ == "__main__":
-    cmd = sys.argv[1] if len(sys.argv) > 1 else "verify"
-    if cmd == "seed":
-        seed(); verify()
-    elif cmd == "verify":
-        sys.exit(0 if verify() else 1)
-    elif cmd == "append":
-        print(json.dumps(append(json.loads(sys.argv[2])), indent=2))
-    else:
-        print(__doc__); sys.exit(2)
@@ -1,41 +0,0 @@
-# AetherArena submission manifest (ADR-149 §2.2).
-# Accompanies a model artifact pushed to the AA Hugging Face Space.
-# This file is the contract the Space validates before quarantine + scoring.
-
-[submission]
-# Free-form display name shown on the leaderboard.
-name = "my-spatial-model"
-# Hugging Face repo or URL of the model artifact (.safetensors / .rvf / LoRA adapter).
-model_ref = "hf://your-org/your-model"
-# Submitter handle (HF username / org). Used to sign the ledger row.
-submitter = "your-hf-username"
-# SPDX license of the submitted model.
-license = "Apache-2.0"
-
-[category]
-# One of: pose | presence | tracking | vitals | multi-task
-# v0 ranks: pose, presence (tracking/vitals activate when ground truth lands).
-primary = "pose"
-
-[input]
-# Which ADR-145 FeatureSet the model consumes. v0 input is RF/WiFi CSI.
-#   F0 = CSI amplitude/phase   F1 = +CIR   F2 = +Doppler   F3 = +BFLD
-feature_set = "F0"
-# Tensor I/O contract so the scorer can feed the model correctly.
-input_shape = [114, 2]      # subcarriers × {amp, phase}  (example)
-output_shape = [17, 2]      # 17 keypoints × {x, y} normalised [0,1]
-# Normalisation expected on the input ("none" | "zscore" | "minmax").
-normalization = "zscore"
-
-[runtime]
-# Inference entrypoint inside the artifact (framework-specific).
-framework = "candle"        # candle | onnx | torch
-# Optional: target the edge-latency category with a declared device class.
-device_class = "cpu"        # cpu | pi5 | gpu
-
-# Notes:
-# - You submit a MODEL, never predictions on data you hold.
-# - Scoring runs against a PRIVATE MM-Fi held-out split in a no-network,
-#   read-only sandbox. You cannot see the eval data.
-# - The resulting score is a signed, append-only ledger row carrying a
-#   determinism proof hash and the pinned harness_version.
@@ -1,37 +0,0 @@
---
-title: AetherArena — Spatial-Intelligence Benchmark
-emoji: 📡
-colorFrom: indigo
-colorTo: purple
-sdk: gradio
-sdk_version: 5.9.1
-python_version: "3.12"
-app_file: app.py
-pinned: true
-license: cc-by-nc-4.0
-tags:
-  - benchmark
-  - leaderboard
-  - wifi-sensing
-  - spatial-intelligence
-  - pose-estimation
---
-
-# AetherArena ("AA") — The Official Spatial-Intelligence Benchmark
-
-> Public leaderboard. Private evaluation split. Open scorer. Signed results.
-
-The field's standard yardstick for camera-free **spatial intelligence** (pose, presence,
-occupancy, tracking, vitals) from RF/WiFi and, over time, mmWave / UWB / multimodal.
-
- **Project-agnostic** — any team, framework, or modality enters; RuView donated the seed
-  scorer and is scored like everyone else.
- **Benchmark-first** — the board starts empty; every row is a real scoring-pipeline
-  **witness** (`inputs_sha256` + `proof_sha256` + `harness_version`) in an append-only,
-  hash-chained, tamper-evident ledger.
- **Reproducible** — the scorer is open; reproduce any proof hash + repeatability locally.
-
-Spec: [ADR-149](https://github.com/ruvnet/RuView/blob/main/docs/adr/ADR-149-public-community-leaderboard-huggingface.md).
-Source + open scorer: https://github.com/ruvnet/RuView/tree/main/aether-arena
-
-Non-commercial (CC BY-NC 4.0): the v0 eval split derives from MM-Fi (CC BY-NC); AA is operated non-commercially.
@@ -1,161 +0,0 @@
-"""AetherArena ("AA") — The Official Spatial-Intelligence Benchmark.
-
-Hugging Face Space (Gradio) — the public face of the benchmark (ADR-149).
-This Space is the presentation + submission layer; the heavy scoring runs in the
-pinned RuView harness (CI / scorer container), and results land in the append-only,
-hash-chained **witness ledger** shown here.
-
-Benchmark-first: the board starts EMPTY. No seeded or hand-entered numbers — every
-row is a real scoring-pipeline witness (inputs_sha256 + proof_sha256 + harness_version).
-"""
-import hashlib
-import json
-from pathlib import Path
-
-import gradio as gr
-
-LEDGER = Path(__file__).parent / "ledger.jsonl"
-GENESIS_PREV = "0" * 64
-
-
-def _rows():
-    if not LEDGER.exists():
-        return []
-    return [json.loads(l) for l in LEDGER.read_text().splitlines() if l.strip()]
-
-
-def _canon(row: dict) -> bytes:
-    body = {k: row[k] for k in sorted(row) if k != "row_hash"}
-    return json.dumps(body, separators=(",", ":"), sort_keys=True).encode()
-
-
-def verify_chain():
-    rows, prev = _rows(), GENESIS_PREV
-    for i, r in enumerate(rows):
-        if r.get("prev_hash") != prev or r.get("row_hash") != hashlib.sha256(_canon(r)).hexdigest():
-            return f"❌ Ledger chain BROKEN at row {i} — tampering detected."
-        prev = r["row_hash"]
-    return f"✅ Witness ledger chain intact — {len(rows)} row(s), append-only."
-
-
-def leaderboard(category: str):
-    results = [r for r in _rows() if r.get("kind") == "result" and (category == "all" or r.get("category") == category)]
-    if not results:
-        return [["— no entries yet —", "", "", "", "", ""]]
-    results.sort(key=lambda r: r.get("score_pct") or 0, reverse=True)
-    return [[
-        r.get("submitter", "?"),
-        r.get("model_ref", "?"),
-        f"{r.get('benchmark','?')} / {r.get('protocol','?')}",
-        r.get("metric", "?"),
-        f"{r.get('score_pct', 0):.2f}%",
-        f"{r.get('tier','?')} (vs {r.get('sota_ref','?')})",
-    ] for r in results]
-
-
-FOUR_PART = "### Public leaderboard. Private evaluation split. Open scorer. Signed results."
-
-ABOUT = """
-**AetherArena** is the official, project-agnostic **Spatial-Intelligence Benchmark** —
-camera-free pose, presence, occupancy, tracking, and vitals from RF/WiFi (and, over
-time, mmWave / UWB / radar / multimodal). It is **not** a single-vendor board: any
-team, framework, or modality enters, and every entrant — including the RuView baseline
-that donated the seed scorer — is scored by the identical, open, pinned harness.
-
-The scorer reuses RuView's released `wifi-densepose-train` acceptance harness
-(`ruview_metrics` + ablation). You submit a **model, not predictions**; it is scored
-against a **private** MM-Fi held-out split; one **witness** row (inputs hash + proof
-hash + harness version) is appended to a **hash-chained, tamper-evident ledger**.
-
-**For industry:** a vendor-neutral, auditable way to compare RF-sensing models on equal
-footing — the same standardized splits, the same metric definition, the same signed,
-reproducible ledger. No more "trust our number on our split." Vendors, labs, and startups
-all submit through one pipeline and are scored identically.
-
-**Generalization Track (roadmap):** the headline isn't a single in-domain number — it's a
-battery of honest tracks: MM-Fi `random_split` (in-domain), `cross_subject` (unseen people),
-cross-room, cross-device, and confidence-calibration (ECE). Cross-subject is the real
-deployment frontier and is treated as the flagship hard benchmark.
-
-Spec: ADR-149. v0 ranks **pose, presence, edge-latency, determinism**. Tracking &
-vitals activate when their ground truth lands; **privacy-leakage** is gated until the
-membership-inference attacker ships. Source + the open scorer:
-https://github.com/ruvnet/RuView/tree/main/aether-arena
-"""
-
-SUBMIT = """
-### Submit a model
-
-1. Write a manifest — [`schema/aa-submission.toml`](https://github.com/ruvnet/RuView/blob/main/aether-arena/schema/aa-submission.toml):
-   declare your model ref, category, the ADR-145 feature set (F0 CSI … F3 BFLD), and the tensor I/O contract.
-2. Provide your model artifact (`.safetensors` / `.rvf` / LoRA adapter).
-3. It moves through `submitted → validated → quarantined → smoke_scored → full_scored → published`,
-   scored in a no-network, read-only sandbox against the private split.
-4. Your signed witness row appears on the leaderboard.
-
-**You submit a model, never predictions** — predictions on data you hold prove nothing.
-"""
-
-VERIFY = """
-### Verify it's fair (you don't have to trust us)
-
-The scorer is open and reproducible. Reproduce the determinism proof + repeatability locally:
-
-```bash
-git clone https://github.com/ruvnet/RuView && cd RuView/v2
-# determinism gate (same as CI):
-cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features
-# repeatability — N runs, one identical proof hash:
-cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --repeat 16
-# verify the append-only witness ledger chain:
-cd ../aether-arena/ledger && python3 ledger_tools.py verify
-```
-
-A stranger must be able to: submit → get a deterministic score → see the signed row →
-rerun the scorer locally → understand why the rank is fair. That is the launch gate (ADR-149 §7).
-"""
-
-with gr.Blocks(title="AetherArena — Spatial-Intelligence Benchmark") as demo:
-    gr.Markdown("# 📡 AetherArena (AA)\n## The Official, Vendor-Neutral Benchmark for WiFi / RF Spatial Sensing")
-    gr.Markdown(FOUR_PART)
-    gr.Markdown(
-        "**An open industry benchmark — for everyone, not any one vendor.** Submit any model, any framework, "
-        "any modality. Every entrant — academic, startup, or incumbent — is scored *identically*: standardized "
-        "protocols (MM-Fi `random_split` / `cross_subject`), matched metrics (torso-PCK@20, the published "
-        "definition), and an auditable, hash-chained **witness ledger** anyone can verify and reproduce.\n\n"
-        "**Why it exists:** WiFi/RF-sensing results are reported with inconsistent splits, metrics, and no "
-        "auditability — so numbers aren't comparable. AetherArena fixes the *measurement*: one protocol, one "
-        "metric, one signed ledger, one-command reproduction. The benchmark is the product; the leaderboard is "
-        "just the scoreboard. (Reference implementation seeded by RuView, ADR-149.)"
-    )
-    chain = gr.Markdown(verify_chain())
-
-    with gr.Tab("🏆 Leaderboard"):
-        gr.Markdown(
-            "### Current standings — MM-Fi WiFi-CSI 2D pose, torso-PCK@20\n"
-            "Ranked, protocol- & metric-matched results. Each row carries its own caveats in the ledger "
-            "(e.g. `random_split` has temporal-adjacency leakage that inflates *all* methods equally — the "
-            "leakage-free `cross_subject` track is the real deployment frontier). **Submit yours — top the board.**"
-        )
-        cat = gr.Dropdown(["all", "pose", "presence"], value="all", label="Category")
-        tbl = gr.Dataframe(
-            headers=["Submitter", "Model", "Benchmark / Protocol", "Metric", "Score", "Tier (vs prior SOTA)"],
-            value=leaderboard("all"), interactive=False, wrap=True,
-        )
-        cat.change(leaderboard, cat, tbl)
-        gr.Markdown(
-            "*Vendor-neutral & benchmark-first: every row is a real, metric- and protocol-matched result — "
-            "no seeded or vendor-favored numbers. Integrity is enforced, not promised: the current top entry's "
-            "score was self-corrected down from an inflated metric (91.86% bbox → 81.63% torso) before it could "
-            "be published. The same scorer and ledger apply to every submitter.*"
-        )
-
-    with gr.Tab("📤 Submit"):
-        gr.Markdown(SUBMIT)
-    with gr.Tab("🔬 Verify"):
-        gr.Markdown(VERIFY)
-    with gr.Tab("ℹ️ About"):
-        gr.Markdown(ABOUT)
-
-if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
@@ -1,5 +0,0 @@
-{"benchmark": "AetherArena", "created": "2026-05-30", "kind": "genesis", "note": "Official Spatial-Intelligence Benchmark \u2014 append-only signed ledger. Entries are real harness scores only; no seeded numbers.", "prev_hash": "0000000000000000000000000000000000000000000000000000000000000000", "row_hash": "940bdc6f0f5dd00f4d89e13a8fa843bab3c9ddf1b8051f426a1701e730249231", "seq": 0, "spec": "ADR-149"}
-{"abs_gain": "+9.38", "benchmark": "MM-Fi", "category": "pose", "caveat": "Protocol-matched MM-Fi random_split result; NOT solved real-world generalization. Random split has temporal/subject-adjacency effects common to this benchmark family. Leakage-free cross-subject is far lower (~11-27%) and is the real deployment frontier.", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20 (||right_shoulder-left_hip|| norm, 17 COCO kpts)", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer (4L/8H ~2M params, temporal-attention)", "prev_hash": "940bdc6f0f5dd00f4d89e13a8fa843bab3c9ddf1b8051f426a1701e730249231", "protocol": "random_split (ratio=0.8, seed=0)", "rel_gain": "+13.0%", "reproduce": "download MM-Fi -> parse_mmfi_zips.py -> train_tf_torso.py X.npy Y.npy split_random.npy (seed 0)", "row_hash": "76598d8e1320d5248f8cd854a8ffa22a99bd2a2f0e0e7f2d2b1df79af16001d5", "score_pct": 81.63, "scored_at": "2026-05-30", "seq": 1, "sota_ref": "MultiFormer 72.25 (CSI2Pose 68.41)", "submitter": "ruvnet", "tier": "Gold"}
-{"abs_gain": "+11.34", "benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer + skeleton-graph head + 3-ensemble + TTA", "note": "Best in-domain. Stacks attention-pooling + transformer + skeleton-graph refine + warmup + TTA + 3-model ensemble. Supersedes the 81.63 single-model entry.", "prev_hash": "76598d8e1320d5248f8cd854a8ffa22a99bd2a2f0e0e7f2d2b1df79af16001d5", "protocol": "random_split (0.8, seed 0)", "row_hash": "5780a4bc3e98eb0e30c1ecfa9091e57b280444fa1f21cd5146797e408580e4ab", "score_pct": 83.59, "scored_at": "2026-05-30", "seq": 2, "sota_ref": "MultiFormer 72.25 (CSI2Pose 68.41)", "submitter": "ruvnet", "tier": "Gold"}
-{"benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer", "note": "Leakage-free generalization to unseen people, shared rooms. Honest deployment-relevant number.", "prev_hash": "5780a4bc3e98eb0e30c1ecfa9091e57b280444fa1f21cd5146797e408580e4ab", "protocol": "cross_subject (official, val=S05,S10,..,S40)", "row_hash": "d989e4e1dbc0182610305fdfbde8b094413b87c913283a46bf41f4afba7a06fd", "score_pct": 64.04, "scored_at": "2026-05-30", "seq": 3, "sota_ref": "(no matched public ref)", "submitter": "ruvnet", "tier": "Silver"}
-{"benchmark": "MM-Fi", "category": "pose", "harness_version": 1, "kind": "result", "metric": "torso-PCK@20", "modality": "wifi-csi", "model_ref": "RuView CSI-Transformer + CORAL domain alignment", "note": "The real deployment frontier (new room). CORAL transductive DG (+30% rel over control). Data-bound: MM-Fi has only 3 source rooms.", "prev_hash": "d989e4e1dbc0182610305fdfbde8b094413b87c913283a46bf41f4afba7a06fd", "protocol": "cross_environment (train E01-03 -> test E04, new room)", "row_hash": "bf370487bde88e198c13877956dab3c83766a6a24afef0b78b6ac7aa130bb207", "score_pct": 17.51, "scored_at": "2026-05-30", "seq": 4, "sota_ref": "(hard frontier; control 13.52)", "submitter": "ruvnet", "tier": "Bronze"}
@@ -1 +0,0 @@
-gradio==5.9.1
@@ -1 +1 @@
-304d54690af468dc6cbf0f2a1332f109cf187d5e2eab454efd8554cebc45bdeb
+120bd7b1f549f57f3773971a389c48c2bdd99b4ab1f205935867a16e95583995
@@ -1 +1 @@
-f8e76f21a0f9852b70b6d9dd5318239f6b20cbcb4cdd995863263cecdc446f7a
+ca58956c1bbee8c46f1798b3d6b6f1f829aa5db90bba53e07177830eca429199
@@ -185,14 +185,7 @@ def frame_to_csi_data(frame, signal_meta):
 # observed pipeline-amplified ULP drift and is still far below any meaningful
 # signal change (CSI phase precision is ~1e-3 rad; PSD bins differ by orders
 # of magnitude). Round to this precision, then hash.
-#
-# NOTE: 6 decimals collapses the divergence *across Linux microarchitectures*
-# but NOT Windows-vs-Linux, where the pocketfft/BLAS difference exceeds 1e-6 on
-# a few elements that then straddle the 6th-decimal rounding boundary. The
-# precision is overridable via PROOF_HASH_DECIMALS so it can be coarsened to a
-# value that is boundary-stable across *all* platforms (Windows + Linux + macOS)
-# while staying far below any signal-meaningful change.
-HASH_QUANTIZATION_DECIMALS = int(os.environ.get("PROOF_HASH_DECIMALS", "6"))
+HASH_QUANTIZATION_DECIMALS = 6


 def features_to_bytes(features):
@@ -212,20 +205,13 @@ def features_to_bytes(features):
    """
    parts = []

-    # Serialize each feature array in declaration order.
-    # doppler_shift is INTENTIONALLY excluded: it is peak-normalized
-    # (`spectrum / max(spectrum)` in csi_processor._extract_doppler_features),
-    # and when the raw spectrum has near-tied peaks the argmax flips under
-    # cross-microarchitecture FP reordering, renormalizing the whole array
-    # (O(1) divergence — not absorbable by any tolerance). The remaining five
-    # features, including the FFT-based PSD, reproduce deterministically and
-    # provide the proof. (The underlying doppler instability is a production
-    # reproducibility bug tracked separately.)
+    # Serialize each feature array in declaration order
    for array in [
        features.amplitude_mean,
        features.amplitude_variance,
        features.phase_difference,
        features.correlation_matrix,
+        features.doppler_shift,
        features.power_spectral_density,
    ]:
        flat = np.asarray(array, dtype=np.float64).ravel()
@@ -239,45 +225,6 @@ def features_to_bytes(features):
    return b"".join(parts)


-# ── Cross-platform tolerance gate (issue #560 follow-up) ─────────────────────
-# The SHA-256 of fixed-decimal-rounded features is bit-exact only WITHIN one
-# CPU microarchitecture. The pocketfft / BLAS kernels in the manylinux
-# numpy/scipy wheels reorder floating-point reductions differently across
-# microarchs (e.g. a GitHub Azure runner vs a developer box vs another Linux
-# host), and the resulting ~1e-6 *relative* drift lands on large-magnitude PSD
-# bins as an absolute difference too large for ANY fixed-decimal grid to absorb
-# (empirically the hash diverges across microarchs even at 2 decimals). So:
-#   • the hash is the strong, bit-exact, SAME-platform proof, and
-#   • a relative tolerance against a committed reference vector is the
-#     platform-INDEPENDENT proof.
-# A run PASSES if either matches. Tolerances sit ~100x over the observed
-# microarch drift and ~10x under any signal-meaningful change (CSI phase
-# precision ~1e-3 rad), so real pipeline regressions still fail.
-TOLERANCE_RTOL = 1e-4
-TOLERANCE_ATOL = 1e-6
-REFERENCE_VECTOR_FILENAME = "expected_features_reference.npz"
-
-
-def features_to_vector(features):
-    """Concatenate a frame's feature arrays as raw float64 (no rounding).
-
-    Mirrors ``features_to_bytes`` ordering but keeps full precision, for the
-    tolerance-based cross-platform comparison.
-    """
-    # doppler_shift excluded — see features_to_bytes for the rationale
-    # (peak-normalization argmax instability across CPU microarchitectures).
-    arrays = [
-        features.amplitude_mean,
-        features.amplitude_variance,
-        features.phase_difference,
-        features.correlation_matrix,
-        features.power_spectral_density,
-    ]
-    return np.concatenate(
-        [np.asarray(a, dtype=np.float64).ravel() for a in arrays]
-    )
-
-
 def compute_pipeline_hash(data_path, verbose=False):
    """Run the full pipeline and compute the SHA-256 hash of all features.

@@ -320,7 +267,6 @@ def compute_pipeline_hash(data_path, verbose=False):
    features_count = 0
    total_feature_bytes = 0
    last_features = None
-    feature_vectors = []
    doppler_nonzero_count = 0
    doppler_shape = None
    psd_shape = None
@@ -337,7 +283,6 @@ def compute_pipeline_hash(data_path, verbose=False):
        if features is not None:
            feature_bytes = features_to_bytes(features)
            hasher.update(feature_bytes)
-            feature_vectors.append(features_to_vector(features))
            features_count += 1
            total_feature_bytes += len(feature_bytes)
            last_features = features
@@ -406,11 +351,7 @@ def compute_pipeline_hash(data_path, verbose=False):
        "psd_shape": psd_shape,
    }

-    reference_vector = (
-        np.concatenate(feature_vectors) if feature_vectors else np.array([], dtype=np.float64)
-    )
-
-    return hasher.hexdigest(), reference_vector, stats
+    return hasher.hexdigest(), stats


 def audit_codebase(base_dir=None):
@@ -526,7 +467,7 @@ def main():
    print("    This runs the SAME CSIProcessor.preprocess_csi_data() and")
    print("    CSIProcessor.extract_features() used in production.")
    print()
-    computed_hash, computed_vector, stats = compute_pipeline_hash(data_path, verbose=args.verbose)
+    computed_hash, stats = compute_pipeline_hash(data_path, verbose=args.verbose)

    # ---------------------------------------------------------------
    # Step 3: Hash comparison
@@ -538,11 +479,8 @@ def main():
        with open(hash_path, "w") as f:
            f.write(computed_hash + "\n")
        print(f"    Wrote expected hash to {hash_path}")
-        ref_path = os.path.join(SCRIPT_DIR, REFERENCE_VECTOR_FILENAME)
-        np.savez_compressed(ref_path, features=computed_vector)
-        print(f"    Wrote reference vector ({computed_vector.size} values) to {ref_path}")
        print()
-        print("  HASH + REFERENCE GENERATED -- run without --generate-hash to verify.")
+        print("  HASH GENERATED -- run without --generate-hash to verify.")
        print("=" * 72)
        return

@@ -561,70 +499,13 @@ def main():

    print(f"    Expected: {expected_hash}")

-    hash_match = computed_hash == expected_hash
-
-    # Cross-platform fallback: if the bit-exact hash differs (different CPU
-    # microarchitecture reorders the pocketfft/BLAS reductions), accept the run
-    # when the raw feature vector matches the committed reference within a
-    # relative tolerance — platform-independent where the hash is not (#560).
-    tolerance_match = False
-    max_abs_dev = None
-    max_rel_dev = None
-    ref_path = os.path.join(SCRIPT_DIR, REFERENCE_VECTOR_FILENAME)
-    if not hash_match and os.path.exists(ref_path):
-        ref_vec = np.load(ref_path)["features"]
-        if ref_vec.shape == computed_vector.shape:
-            tolerance_match = bool(
-                np.allclose(
-                    computed_vector, ref_vec, rtol=TOLERANCE_RTOL, atol=TOLERANCE_ATOL
-                )
-            )
-            diff = np.abs(computed_vector - ref_vec)
-            max_abs_dev = float(np.max(diff)) if diff.size else 0.0
-            max_rel_dev = (
-                float(np.max(diff / np.maximum(np.abs(ref_vec), 1e-12)))
-                if diff.size
-                else 0.0
-            )
-
-    if hash_match:
-        match_status = "MATCH (bit-exact)"
-    elif tolerance_match:
-        match_status = f"TOLERANCE MATCH (max rel dev {max_rel_dev:.2e})"
+    if computed_hash == expected_hash:
+        match_status = "MATCH"
    else:
        match_status = "MISMATCH"
    print(f"    Status:   {match_status}")
    print()

-    if not hash_match and max_abs_dev is not None:
-        block_sizes = [56, 56, 55, 9, 128]  # per-frame feature layout (doppler excluded)
-        block_names = ["amp_mean", "amp_var", "phase_diff", "corr", "psd"]
-        frame_len = sum(block_sizes)
-        tol = TOLERANCE_ATOL + TOLERANCE_RTOL * np.abs(ref_vec)
-        outside = diff > tol
-        n_out = int(outside.sum())
-        print(
-            f"    DIVERGENCE: {n_out}/{computed_vector.size} outside tol "
-            f"({100.0 * n_out / computed_vector.size:.4f}%)  "
-            f"max|d|={max_abs_dev:.3e} maxrel={max_rel_dev:.3e}"
-        )
-        if n_out:
-            wf = np.where(outside)[0] % frame_len
-            bounds = np.cumsum([0] + block_sizes)
-            parts = []
-            for bi, name in enumerate(block_names):
-                c = int(((wf >= bounds[bi]) & (wf < bounds[bi + 1])).sum())
-                if c:
-                    parts.append(f"{name}={c}")
-            print(f"    by feature: {', '.join(parts)}")
-            for w in np.argsort(diff)[::-1][:4]:
-                b = int(np.searchsorted(bounds, int(w) % frame_len, side="right")) - 1
-                print(
-                    f"      worst idx {int(w)} ({block_names[b]}): "
-                    f"ref={ref_vec[int(w)]:.6g} got={computed_vector[int(w)]:.6g}"
-                )
-        print()
-
    # ---------------------------------------------------------------
    # Step 4: Audit (if requested or always in full mode)
    # ---------------------------------------------------------------
@@ -647,22 +528,14 @@ def main():
    # Final verdict
    # ---------------------------------------------------------------
    print("=" * 72)
-    if hash_match or tolerance_match:
+    if computed_hash == expected_hash:
        print("  VERDICT: PASS")
        print()
-        if hash_match:
-            print("  The pipeline produced a SHA-256 hash that matches the published")
-            print("  expected hash (bit-exact). This proves:")
-        else:
-            print("  The bit-exact hash differs (CPU-microarchitecture FP reordering),")
-            print("  but the raw feature vector matches the published reference within")
-            print(
-                f"  rtol={TOLERANCE_RTOL:g} / atol={TOLERANCE_ATOL:g} "
-                f"(max rel dev {max_rel_dev:.2e}). This proves:"
-            )
+        print("  The pipeline produced a SHA-256 hash that matches the published")
+        print("  expected hash. This proves:")
        print("    1. The SAME signal processing code ran on the reference signal")
        print("    2. The output is DETERMINISTIC (same input -> same output)")
-        print("    3. No randomness was introduced")
+        print("    3. No randomness was introduced (hash would differ)")
        print("    4. The code path includes: noise removal, Hamming windowing,")
        print("       amplitude normalization, FFT-based Doppler extraction,")
        print("       and power spectral density computation")
@@ -673,19 +546,14 @@ def main():
    else:
        print("  VERDICT: FAIL")
        print()
-        print("  The pipeline output does NOT match the expected hash OR the")
-        print("  reference feature vector within tolerance.")
-        if max_rel_dev is not None:
-            print(
-                f"    max abs dev: {max_abs_dev:.3e}   max rel dev: {max_rel_dev:.3e}"
-                f"   (rtol={TOLERANCE_RTOL:g}, atol={TOLERANCE_ATOL:g})"
-            )
+        print("  The pipeline output does NOT match the expected hash.")
        print()
        print("  Possible causes:")
+        print("    - Numpy/scipy version mismatch (check requirements)")
        print("    - Code change in CSI processor that alters numerical output")
-        print("    - A real (non-microarch) numerical regression")
+        print("    - Platform floating-point differences (unlikely for IEEE 754)")
        print()
-        print("  To update after an intentional change:")
+        print("  To update the expected hash after intentional changes:")
        print("    python verify.py --generate-hash")
        print("=" * 72)
        sys.exit(1)
@@ -6,14 +6,8 @@
 #
 # To update: change versions, run `python v1/data/proof/verify.py --generate-hash`,
 # then commit the new expected_features.sha256.
-#
-# numpy/scipy track the versions the *published* expected hash
-# (expected_features.sha256 = ca58956c…) was generated with — modern numpy 2.x,
-# i.e. what a fresh `pip install numpy` and the proof-of-capabilities.md skeptic
-# path produce today. The old 1.26.4 pin no longer matched that hash and made
-# the determinism gate fail against its own published proof.

-numpy==2.4.2
-scipy==1.17.1
+numpy==1.26.4
+scipy==1.14.1
 pydantic==2.10.4
 pydantic-settings==2.7.1
@@ -221,15 +221,11 @@ class ESP32BinaryParser:

        snr = float(rssi - noise_floor)
        frequency = float(freq_mhz) * 1e6
+        bandwidth = 20e6  # default; could infer from n_subcarriers

-        # Bandwidth inference (issue #1005): HE-LTF uses a 4x denser tone
-        # grid than HT-LTF on the same channel width — an HE-SU frame with
-        # 256 bins (242 active HE20 tones) is a *20 MHz* capture, not 160.
-        if ppdu_byte in (1, 2, 3):  # HE-SU / HE-MU / HE-TB
-            bandwidth = 40e6 if (flags_byte & 0x01) or n_subcarriers > 256 else 20e6
-        elif n_subcarriers <= 64:  # ESP32 HT20 delivers the full 64-bin FFT
+        if n_subcarriers <= 56:
            bandwidth = 20e6
-        elif n_subcarriers <= 128:
+        elif n_subcarriers <= 114:
            bandwidth = 40e6
        elif n_subcarriers <= 242:
            bandwidth = 80e6
@@ -107,25 +107,16 @@ class PoseService:
    async def _initialize_models(self):
        """Initialize neural network models."""
        try:
-            # Initialize DensePose model. DensePoseHead requires a config
-            # dict — input_channels matches the modality translator's output
-            # (256), with the standard DensePose 24 body parts and 2 (U,V)
-            # coordinates. (Previously called with no args → TypeError at
-            # startup, which broke the API service.)
-            densepose_config = {
-                'input_channels': 256,
-                'num_body_parts': 24,
-                'num_uv_coordinates': 2,
-            }
+            # Initialize DensePose model
            if self.settings.pose_model_path:
-                self.densepose_model = DensePoseHead(densepose_config)
+                self.densepose_model = DensePoseHead()
                # Load model weights if path is provided
                # model_state = torch.load(self.settings.pose_model_path)
                # self.densepose_model.load_state_dict(model_state)
                self.logger.info("DensePose model loaded")
            else:
                self.logger.warning("No pose model path provided, using default model")
-                self.densepose_model = DensePoseHead(densepose_config)
+                self.densepose_model = DensePoseHead()
            
            # Initialize modality translation
            config = {
@@ -1,137 +0,0 @@
-# Edge-Latency Benchmark Results — ADR-163
-
-Converting **CLAIMED** edge latency budgets into **MEASURED-on-host** numbers,
-closing the measurement debt flagged by Milestones 5/6 (ADR-159 / ADR-160).
-Benches + docs only — **no production-code behavior changed**.
-
-## The honest caveat, up front (read before citing any number)
-
-Two distinct gaps separate every number below from the figure it is converting:
-
-1. **Host ≠ ESP32.** The wasm-edge skill modules document budgets *"on ESP32-S3
-   WASM3"* (e.g. `exo_time_crystal`: "H (<10 ms)"). These benches run **native
-   x86_64 on a development laptop**, not the Xtensa/WASM3 target. A native host
-   median is an **upper bound on the algorithm's work**, not the ESP32 number.
-   WASM3 interpretation on a ~240 MHz Xtensa core is typically 1–2 orders of
-   magnitude slower than native `-O` host code, so a host median far under the
-   budget **does NOT prove the ESP32 meets it.** *The ESP32 figure is NOT
-   reproduced here — it needs hardware.*
-
-2. **Bench ≠ the doc-claimed measurement.** For the cogs, the manifest cites a
-   **cold-start** number (`cold_start_ms_avg`, weight-load included); these
-   benches measure **steady-state** per-frame `infer` (warm, weights resident).
-   Different measurements; we report both, labelled.
-
-Grades (per `benchmarks/wiflow-std/RESULTS.md` / ADR-152 vocabulary):
- **MEASURED-on-host** — reproduced in this repo on the machine below, exact
-  command recorded. NOT the ESP32 / NOT the cold-start figure.
- **CLAIMED (ESP32)** — the doc budget; UNMEASURED on hardware here.
-
-## Machine
-
-| | |
-|---|---|
-| Host | `ruvzen` (Windows 11, this dev box) |
-| CPU | Intel Core Ultra 9 285H |
-| Toolchain | `cargo 1.91.1`, `--release` (opt-level per crate profile) |
-| Bench harness | criterion 0.5 (`time: [low **median** high]` reported below) |
-| Date | 2026-06-12 |
-
-Run-to-run spread on this box is non-trivial (criterion's low/high bracket the
-median by a few %); the medians below are single-session captures with the smoke
-settings `--warm-up-time 1 --measurement-time 2` (wasm-edge) / `3` (cogs). Re-run
-for your own machine — the absolute numbers are host-specific.
-
---
-
-## T1 — wasm-edge `process_frame` hot paths (ADR-160 deferred item → DONE host)
-
-The crate is **excluded from the v2 workspace**; bench from the crate dir.
-
-```bash
-cd v2/crates/wifi-densepose-wasm-edge
-cargo bench --features std -- --warm-up-time 1 --measurement-time 2
-# med_seizure_detect is medical-experimental-gated:
-cargo bench --features std,medical-experimental -- --warm-up-time 1 --measurement-time 2 med_seizure
-```
-
-| Hot path (M6-audit-named) | Bench id | Host median | Grade | Doc budget (CLAIMED, ESP32) |
-|---|---|---|---|---|
-| `exo_time_crystal` 256-pt × 128-lag autocorrelation (full buffer) | `exo_time_crystal::process_frame[autocorr_256x128]` | **17.3 µs** | MEASURED-on-host | "H (<10 ms) on ESP32-S3 WASM3" — **NOT reproduced here (needs hardware)** |
-| `exo_ghost_hunter` empty-room periodicity + hidden-breathing | `exo_ghost_hunter::process_frame[empty_room_periodicity]` | **1.44 µs** | MEASURED-on-host | research/exotic; no firm ESP32 figure — host proxy only |
-| `sec_weapon_detect` per-subcarrier Welford (MAX_SC=32) | `sec_weapon_detect::process_frame[per_sc_welford]` | **0.42 µs** (420 ns) | MEASURED-on-host | research-grade; calibration-gated — host proxy only |
-| `med_seizure_detect` clonic-phase rhythm path (steady-state frame) | `med_seizure_detect::process_frame[clonic_rhythm]` | **0.10 µs** (105 ns) | MEASURED-on-host (feature-gated) | doc budget "S (<5 ms) on ESP32"; **NOT reproduced here** |
-
-Reading these honestly:
-
- `exo_time_crystal` at **17.3 µs host** is the only one whose host cost is even
-  in the same *thousandths* of its 10 ms ESP32 budget — it does the most work
-  (~32K MACs/frame). 17.3 µs native says the algorithm is cheap; it says
-  **nothing** about whether WASM3-on-Xtensa lands under 10 ms. A naïve
-  host→ESP32 extrapolation (assume 100× interpreter+clock penalty) would put it
-  near ~1.7 ms, comfortably under — **but that is an extrapolation, not a
-  measurement**, and is recorded here only to show the host number is not
-  obviously in tension with the budget. ESP32 figure: **UNMEASURED**.
- `med_seizure_detect`'s 105 ns is the **steady-state** per-frame cost; the
-  expensive clonic autocorrelation only fires when the state machine is in the
-  clonic phase, so this is a lower-bound on the heavy path, not the worst case.
-  It is still a real, committed host datapoint.
- The pre-existing `tests/budget_compliance.rs` already asserts the L/S/H
-  wall-clock tiers (25 passing tests); these criterion benches add the
-  regression-grade, reproducible median that ADR-160 deferred.
-
---
-
-## T2 — cog steady-state inference latency (ADR-159/160 deferred item → DONE)
-
-Cog crates are normal workspace members; bench from `v2/`. Real weights
-(`count_v1.safetensors` / `pose_v1.safetensors`) ship in-repo under each cog's
-`cog/artifacts/`, so the bench measures the **real Candle CPU forward**, not the
-stub (the bench `assert!`s `backend().starts_with("candle-")`).
-
-```bash
-cd v2
-cargo bench -p cog-person-count  --no-default-features --bench infer_bench -- --warm-up-time 1 --measurement-time 3
-cargo bench -p cog-pose-estimation --no-default-features --bench infer_bench -- --warm-up-time 1 --measurement-time 3
-```
-
-| Cog | Bench id | Host median (steady-state infer, CPU) | Grade | Manifest cold-start (CLAIMED, different measurement + machine) |
-|---|---|---|---|---|
-| cog-person-count | `cog_person_count::infer[cpu_real_weights_steady_state]` | **305 µs** (idle box) | MEASURED-on-host | — (person-count manifest carries comparable provenance) |
-| cog-pose-estimation | `cog_pose_estimation::infer[cpu_real_weights_steady_state]` | **305 µs** (idle box) | MEASURED-on-host | `cold_start_ms_avg: 5.4` (30 invocations, **ruvultra/RTX 5080 host**, candle 0.9 cpu) — **cold-start, NOT steady-state; NOT this machine** |
-
-> Spread caveat (observed, honest): both medians above were captured with the box
-> otherwise idle. A re-run of the validate-form command *while a second cargo job
-> was loading the same cores* gave 385 µs (person-count) / 973 µs (pose) —
-> the criterion low/high bracket widens to ~0.34–1.18 ms under contention. The
-> 305 µs figures are the idle-box datapoints; the absolute number is host- and
-> load-dependent (the ~10× pose swing is core contention, not a code change).
-
-Reading these honestly:
-
- **Steady-state ≠ cold-start.** The pose manifest's `5.4 ms` folds in one-time
-  weight load / mmap / first-forward allocation. This bench warms the engine
-  first and times only the recurring per-frame forward, on a *different
-  machine*. The two numbers are not comparable and we do not claim this bench
-  reproduces the 5.4 ms manifest figure.
- Both cogs share the same conv encoder; person-count adds a count head +
-  confidence head, pose adds a 256-wide MLP head. The host steady-state cost is
-  dominated by the three dilated Conv1d layers (56→64→128→128) shared by both —
-  which is why both land at ~305 µs.
- **Empirical confirmation of the steady-state/cold-start gap:** pose
-  steady-state (305 µs host) is ~18× *under* the manifest's 5.4 ms cold-start.
-  Even accounting for the different machine, this is the expected shape — the
-  bulk of cold-start is one-time setup, not the forward pass — and it is exactly
-  why conflating the two would be dishonest.
-
---
-
-## Status vs the deferred items
-
-| Deferred item | Was | Now |
-|---|---|---|
-| ADR-160 "Criterion benches for `process_frame` budget claims" | ACCEPTED-FUTURE | **DONE (host)**; ESP32-on-hardware still **PENDING** (needs the wasm32 target + a flashed ESP32-S3) |
-| ADR-159/160 cog inference latency (`cold_start_ms_avg` uncommitted-benched) | CLAIMED | **MEASURED-on-host (steady-state)**; cold-start-on-ruvultra remains the manifest's separate claim |
-
-Nothing here changes runtime behavior — these are benches + this results file
-only. No crate needs republishing.
@@ -1,132 +0,0 @@
-# Edge-Skill Synthetic-Ground-Truth Validation — RESULTS
-
-**Crate:** `v2/crates/wifi-densepose-wasm-edge` (workspace-EXCLUDED — build from its own dir)
-**Branch:** `feat/edge-skills-synthetic-validation`
-**ADR:** [ADR-160](../../docs/adr/ADR-160-edge-skill-library-honest-labeling.md)
-**Date:** 2026-06-13
-**Harness:** `tests/synthetic_validation.rs`
-
-> **HONESTY BOUNDARY — read first.** Everything below is **synthetic-ground-truth
-> validation**: a signal is *planted* with a known answer, the **real** detector
-> is run, and detection accuracy / precision / recall / rate-error is **measured**.
-> This is **NOT field accuracy.** A skill that recovers a planted sinusoid here is
-> proven to do the math it claims on a *constructed* signal; it is **NOT** proven
-> to work on real CSI in a real room. Skills whose detection target cannot be
-> honestly planted (clinical, weapon, affect, sleep-stage, sign-language) are
-> **NOT** given a number — they are listed under **DATA-GATED** with the real
-> data each would require.
-
-## Reproduce
-
-```bash
-cd v2/crates/wifi-densepose-wasm-edge   # workspace-excluded; build here
-cargo test --features std --test synthetic_validation -- --nocapture
-# also runs under the medical tier (med_* skills stay DATA-GATED, not validated):
-cargo test --features std,medical-experimental --test synthetic_validation -- --nocapture
-```
-
-Each `MEASURED-on-synthetic | …` line printed by the harness is the source of the
-table below. Numbers are deterministic (no RNG; pseudo-noise uses a fixed LCG seed).
-
---
-
-## MEASURED-on-synthetic (constructible skills)
-
-| Skill | What was planted (ground truth) | Result | Grade |
-|-------|----------------------------------|--------|-------|
-| **vital_trend** | BPM held N≥6 calls at each threshold band (brady/tachy-pnea <12 / >25, brady/tachy-cardia <50 / >120, apnea breathing<1.0 for ≥20) vs normal | **acc 1.000, prec 1.000, recall 1.000** (TP5 FP0 TN5 FN0) | MEASURED |
-| **exo_time_crystal** | period-2 coordinated motion vs pseudo-noise + flat | **acc 1.000** (TP1 FP0 TN2 FN0) | MEASURED † |
-| **exo_ghost_hunter** (hidden breathing) | phase sinusoid at lag-8 (breathing band 5–15) in an empty room vs flat phase | **acc 1.000**; planted score **1.000**, flat **0.000** | MEASURED |
-| **occupancy** | 220-frame flat-amplitude calibration, then strong per-zone amplitude variance vs flat | **acc 1.000** (TP1 FP0 TN1 FN0) | MEASURED |
-| **intrusion** | calibrate→arm (330 quiet frames), then per-subcarrier Δphase>1.5 + Δamp≫3σ vs quiet | **acc 1.000** (TP1 FP0 TN1 FN0) | MEASURED |
-| **exo_rain_detect** | empty room, 60-frame baseline, then broadband variance (8/8 groups, ratio≫2.5) for ≥10 frames vs stable-low | **acc 1.000** (TP1 FP0 TN1 FN0) | MEASURED |
-| **sig_flash_attention** | sustained high phase+amplitude in each of the 8 subcarrier groups; assert reported attention peak == planted group | **peak-localization 8/8 = 1.000** | MEASURED |
-| **spt_spiking_tracker** | sparse (2-subcarrier) large phase-delta in each of the 4 zones; assert tracked zone == planted zone | **zone-localization 4/4 = 1.000** | MEASURED ‡ |
-| **sig_optimal_transport** | sustained large frame-to-frame amplitude-distribution change vs stationary | **acc 1.000** (TP1 FP0 TN1 FN0) | MEASURED |
-| **sig_mincut_person_match** | 2 persons with distinct stable per-region variance signatures over 40 frames | **person ids assigned, 0 id-swaps / 40 frames** | MEASURED |
-| **lrn_dtw_gesture_learn** | stillness → 3 identical gesture rehearsals → enrollment | **template enrolled (templates=1)** | MEASURED (enroll) §|
-| **sig_sparse_recovery** | 30 clean frames to init, then 8/32 (25%) nulled subcarriers | **dropout-detect + recovery-trigger = PASS** | MEASURED (trigger) ¶|
-
-### Caveats on individual results
-
-† **exo_time_crystal — honest discriminative limit.** A *pure* periodic signal
-already has autocorrelation peaks at lag L **and** 2L (natural harmonics), so this
-"period-doubling" detector cannot separate a true period-2 sub-harmonic from a
-plain periodic signal — an earlier plant using a clean sine produced a *false
-positive* (recorded during development). The construct it **can** discriminate
-with known ground truth is **periodic-coordination vs aperiodic** (noise/flat),
-which is what is measured (1.000). The original "sub-harmonic vs clean period"
-claim is **NOT** validatable with this algorithm.
-
-‡ **spt_spiking_tracker — plant must be sparse.** With weights init'd home=1.0 /
-cross=0.25, firing all 8 inputs in a zone (8×0.25=2.0 > threshold 1.0) overdrives
-*every* output neuron and the tracker collapses to zone 0 (measured 1/4 during
-development). Firing only 2 inputs (home 2.0 fires, cross 0.5 silent) yields clean
-4/4 zone localization. The validatable claim is *single-zone* localization.
-
-§ **lrn_dtw_gesture_learn — enrollment validated; replay-match NOT.** The
-deterministic, constructible part (stillness → 3 identical rehearsals → a template
-is enrolled) is MEASURED. The DTW *replay match* (731) did **not** fire on the
-identical replay in this run (`match_same=false`) — replay-recognition accuracy is
-**reported, not asserted**, and is not claimed as validated.
-
-¶ **sig_sparse_recovery — trigger validated; recovery accuracy is NEGATIVE.**
-The dropout-detection + ISTA-recovery *trigger* pipeline fires correctly on >10%
-planted nulls (asserted). But the **measured recovery accuracy is NOT a win**:
-recovered RMSE **1.0045** vs unrecovered-null RMSE **0.9830** (**−2.2%**, i.e.
-slightly *worse* than leaving the nulls at zero) on a neighbor-correlated signal.
-The tridiagonal correlation model's fixed point does not equal the planted truth.
-**The recovery's reconstruction quality is therefore NOT validated as effective on
-synthetic data** — only its detection/trigger path is. Reported honestly; no
-positive number claimed.
-
---
-
-## DATA-GATED — NOT validatable on synthetic data
-
-Planting a "seizure-like" / "weapon-like" / "happy-like" synthetic signal and
-claiming the detector "works" validates **nothing real** and is exactly the
-AI-slop this project fights. These skills run real DSP (per ADR-160, 0 stubs) and
-keep their ADR-160 disclaimers, but get **no accuracy number** here. Each needs
-the specific real, labelled data listed:
-
-| Skill | Why not constructible on synthetic | Real data required |
-|-------|------------------------------------|--------------------|
-| `med_seizure_detect` | "seizure-like" motion is not a seizure; no ground-truth signature exists synthetically | Clinical EEG-/video-labelled tonic-clonic seizure CSI from instrumented patients |
-| `med_sleep_apnea` | a planted breathing-pause is not clinical apnea (AHI scoring, hypopnea, desaturation) | Polysomnography-labelled (PSG) overnight CSI with scored apnea/hypopnea events |
-| `med_cardiac_arrhythmia` | a synthetic HR sequence cannot encode true arrhythmia morphology | ECG-labelled CSI (AFib/PVC/etc.) from clinical monitoring |
-| `med_respiratory_distress` | distress is a clinical gestalt, not a plantable rate | Clinician-labelled respiratory-distress CSI episodes |
-| `med_gait_analysis` | clinical gait metrics need a reference motion-capture standard | Mocap-/force-plate-labelled gait CSI |
-| `sec_weapon_detect` | a high variance ratio is RF reflectivity, **not** weapon discrimination (ADR-160 §A3 already renamed the event to `HIGH_METAL_REFLECTIVITY`) | Labelled metal-object-vs-no-object CSI with controlled object classes |
-| `exo_emotion_detect` | affect is not recoverable from a planted heuristic; outputs are proxies (ADR-160 §A2) | Validated affect-labelled CSI (self-report / physiological ground truth) |
-| `exo_happiness_score` | "happiness" is a gait-energy proxy, not a measured affect (ADR-160 §A2) | Validated affect/valence-labelled CSI |
-| `exo_dream_stage` | sleep staging needs PSG reference (EEG/EOG/EMG) | PSG-staged overnight CSI |
-| `exo_gesture_language` | coarse gesture clusters ≠ true sign language (ADR-160 §A4) | Labelled ASL letter/word CSI dataset |
-
-> The above are **not failures** — they are the honest boundary. A smaller set of
-> genuinely-measured skills plus this explicit gated list is the deliverable, per
-> the prove-everything directive.
-
---
-
-## Skills not in either list
-
-The remaining edge skills (smart-building / retail / industrial occupancy-style,
-the other `sig_*`/`lrn_*`/`spt_*`/`tmp_*`/`qnt_*`/`aut_*`/`ais_*` algorithm-named
-modules) are **wired and exercised live** in the unified pipeline integration test
-(`tests/pipeline_all.rs`, all 59 default / 64 medical skills run without panic over
-300 synthetic frames) but were **not** given an individual planted-ground-truth
-accuracy number here. They are honest REAL-DSP modules (ADR-160) whose physical
-observable could be planted with more harness work; that is deferred, not claimed.
-
-## Test counts (full crate suite)
-
-```
-DEFAULT  (--features std):                     631 passed, 0 failed
-  (lib 504; budget 25; honest_labeling 10; pipeline_all 4; synthetic_validation 12; bench 1; vendor 75)
-MEDICAL  (--features std,medical-experimental): 669 passed, 0 failed
-  (lib 542; +16 same new tests; med_* stay DATA-GATED, not validated)
-```
-
-(M6 baseline was 615 / 653; the new pipeline_all (4) + synthetic_validation (12)
-tests add 16 to each tier.)
@@ -1,26 +0,0 @@
-# Upstream clone (WiFlow-STD, DY2434) -- never commit third-party code/weights
-upstream/
-
-# Local python env
-.venv/
-
-# Downloaded data / artifacts
-data/
-downloads/
-*.pth
-*.pt
-*.npy
-*.npz
-*.zip
-*.mat
-*.safetensors
-results/parity_fixture.json
-__pycache__/
-*.onnx
-
-# Committed ground truth: corruption masks for the pristine Kaggle download.
-# remote/clean_v2.py zeroes the corrupted source windows IN PLACE, so these
-# masks CANNOT be regenerated from a cleaned copy (generate_corruption_masks.py
-# documents the criteria and reproduces them only from a fresh download).
-!results/nan_windows_mask.npy
-!results/big_windows_mask.npy
@@ -1,486 +0,0 @@
-# WiFlow-STD (DY2434) Benchmark Results — ADR-152 §2.2
-
-Upstream: <https://github.com/DY2434/WiFlow-WiFi-Pose-Estimation-with-Spatio-Temporal-Decoupling>
-pinned at `06899d29` (2026-04-05), Apache-2.0. Dataset: Kaggle `kaka2434/wiflow-dataset`
-(12.8 GB archive → 15.5 GB extracted; 360,000 windows of 540×20 CSI + 15-keypoint 2D labels).
-
-Published claims (README "Setting 1"): PCK@20 97.25%, PCK@30 98.63%, PCK@40 99.16%,
-PCK@50 99.48%, MPJPE 0.007 m, 2.23M params, 0.07 GFLOPs.
-
-## Measurement (a): their model on their data
-
-### Artifact verification (MEASURED, 2026-06-10, this repo `eval_repro.py`)
-
-| Check | Result |
-|---|---|
-| Parameter count | **2,225,042 (2.23M) — matches claim** |
-| FLOPs (torch profiler, batch 1) | ~0.055 GFLOPs — consistent with 0.07B claim |
-| CPU latency (Windows box, torch 2.12 CPU) | 13.2 ms/window @ batch 1 (76/s); 2.48 ms/sample @ batch 64 (403/s) |
-| Checkpoint load | `weights_only=True` (no pickle code execution) |
-
-### Released checkpoint does NOT reproduce the claims — REFUTED as shipped
-
-Running the released `best_pose_model.pth` through the released code on the released
-dataset with the released split procedure (seed-42 file-level 70/15/15; 54,000 test
-samples) yields:
-
-| Metric | Published | Measured (shipped checkpoint) |
-|---|---|---|
-| PCK@20 | 97.25% | **0.08%** |
-| PCK@30 | 98.63% | 0.78% |
-| PCK@40 | 99.16% | 5.53% |
-| PCK@50 | 99.48% | 15.42% |
-| MPJPE | 0.007 | **NaN** (dataset contains NaN CSI windows) |
-
-Raw output: `results/repro_a.json`.
-
-Diagnostics (on 2,000 NaN-free windows from the first files of the dataset, i.e.
-mostly would-be *training* data — so this is not a split mismatch):
-
- Predictions correlate with targets (Pearson r ≈ 0.76) — the checkpoint is a trained
-  model, but in a **different keypoint normalization/order** than the released data.
- Best-case post-hoc global per-axis affine correction: PCK@20 ≈ 20%.
- Best-case per-keypoint affine correction (15×2 fitted transforms — generous
-  cheating): PCK@20 ≈ 72%, still far below 97.25%.
- Pred↔target keypoint correspondence matrix is degenerate (multiple predicted
-  keypoints best-match the same target joint) — keypoint convention mismatch.
-
-### Reproducibility defects in the released artifacts
-
-1. `models/__init__.py` imports `TemporalConvNet`, which `models/tcn.py` does not
-   define — **the published code does not import/run as-is**.
-2. The released root checkpoint uses pre-rename module names (`att.*`, `final_conv.*`)
-   vs the published code (`attention.*`, `decoder.*`) — same shapes/param count, but
-   confirms the checkpoint predates the published code.
-3. The second shipped checkpoint (`cross_dataset_test/WiFlow/best_pose_model.pth`) is
-   a **different architecture** (342-channel input = MM-Fi layout, 3 TCN layers,
-   3-channel/3D decoder) — not usable on their own dataset.
-4. `run.py` ignores `--data_dir` and hardcodes `../preprocessed_csi_data`.
-5. The released dataset's final 13 files (indices 487–499; 9,072 windows, 2.52%)
-   are corrupted: NaN values plus garbage amplitudes up to 3.4e38 (float32 max) in
-   data that is otherwise [0,1]-normalized. Upstream code has no NaN/inf handling;
-   training as published on this download diverges — the first corrupted batch
-   overflows fp16 autocast and permanently poisons BatchNorm running statistics
-   (GradScaler step-skipping does not protect BN). The authors' training curves
-   show normal convergence, so their local data evidently differed from the
-   Kaggle upload. Window masks: `results/nan_windows_mask.npy`,
-   `results/big_windows_mask.npy`.
-
-### Reproducing the corruption masks
-
-The two mask files (9,070 NaN/Inf windows, 9,072 with |amplitude| > 1.5;
-union 9,072, all in dataset files 487–499) are **committed ground truth**
-(gitignore-negated, ~352 KB each). They can only be regenerated from a
-**pristine** Kaggle download: `remote/clean_v2.py` repairs the dataset by
-zeroing the corrupted windows in place, after which the corruption evidence
-is gone and a rescan returns all-False. `generate_corruption_masks.py`
-re-derives them (chunked scan, criteria: any non-finite value OR
-max |finite| > 1.5 per 540×20 window) and refuses to write all-False masks,
-which indicate a cleaned copy. Verified 2026-06-11: a regeneration from the
-local pristine download is bit-identical to the committed masks.
-
-### Retraining result (MEASURED, 2026-06-10): claims APPROXIMATELY REPRODUCED
-
-Since the shipped checkpoint is unusable, measurement (a) fell back to retraining
-with upstream code + defaults (seed 42, batch 64, early-stopped at epoch 41 of 50,
-best epoch 36, ~75 s/epoch) on ruvultra (RTX 5080). Deviations, all forced and
-documented: one-line fix for defect (1); torch 2.x+cu128 instead of pinned 2.3.1
-(Blackwell sm_120 unsupported); the 9,072 corrupted windows (defect 5) zeroed
-entirely — without this the published pipeline produces NaN from epoch 1 (observed).
-Scripts mirrored in `remote/`; raw metrics in `results/eval_retrained.json`.
-
-| Metric | Published | Retrained (full test, 54,000) | Retrained (corruption-free, 52,560) |
-|---|---|---|---|
-| PCK@20 | 97.25% | **96.09%** | **96.61%** |
-| PCK@30 | 98.63% | 97.89% | 98.23% |
-| PCK@40 | 99.16% | 98.58% | 98.79% |
-| PCK@50 | 99.48% | 98.99% | 99.11% |
-| MPJPE | 0.007 | 0.0098 | 0.0094 |
-
-Within ~0.6–1.2 PCK points of every published figure (single run, corrupted train
-windows zeroed, different torch/GPU). **Verdict: the accuracy claims are credible
-and approximately reproducible — but only after repairing the released dataset and
-code.** Val best: PCK@20 96.99%, MPJPE 0.0086 (epoch 36).
-
-One more defect found during the run:
-
-6. `train.py` calls `plot_training_history`, which is not defined anywhere — the
-   built-in post-training test evaluation is unreachable as published (crashes
-   with NameError after training completes).
-
-## ADR-152 §2.2 citation rule
-
-Evidence grade for the WiFlow-STD accuracy claims after measurement (a):
-**MEASURED-EQUIVALENT (96.1–96.6% PCK@20 reproduced by retraining; shipped
-checkpoint REFUTED; dataset/code require repairs)**. RuView docs may cite
-"~96% PCK@20 (our reproduction)" — still **not comparable** to our 17-keypoint
-ESP32 numbers (different hardware, 5 subjects, in-domain random split,
-15 keypoints).
-
-## Edge optimization (measured)
-
-ADR-152 "optimize beyond SOTA" track, 2026-06-10, this Windows box (Windows 11,
-16 torch threads, torch 2.12.0+cpu, onnxruntime 1.26.0). Subject: the retrained
-checkpoint `results/retrained_best_pose_model.pth` (2,225,042 fp32 params).
-Scripts: `quantize_bench.py`, `onnx_bench.py`, `eval_ort_accuracy.py`.
-Raw numbers: `results/edge_optimization.json`.
-
-Accuracy is on a **10,000-window seed-42 random subset** of the corruption-free
-test split (same seed-42 file-level 70/15/15 split as `eval_repro.py`; 54,000
-test windows, 1,440 corrupted excluded via `results/nan_windows_mask.npy` |
-`results/big_windows_mask.npy`, leaving 52,560; subset drawn with
-`np.random.default_rng(42)`). The fp32 subset PCK@20 (96.68%) matches the full
-clean-test figure (96.61%), so the subset is representative.
-
-Latency is CPU ms/window, median of repeated runs, 3 interleaved repetitions
-per variant (medians below; run-to-run spread on this box is large, roughly
-±20-40% at batch 1 — reps are in the JSON).
-
-| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
-|---|---|---|---|---|---|---|
-| torch fp32 (baseline) | 9.07 MB | 11.0 | 2.27 | 96.68% | 99.15% | 0.00936 |
-| torch fp16 (`.half()`) | **4.58 MB** | 24.3 | 2.42 | 96.68% | 99.15% | 0.00946 |
-| torch int8 dynamic | 9.07 MB (unchanged) | 15.6 | 2.06 | 96.68% (identical) | 99.15% | 0.00936 |
-| ONNX fp32 (onnxruntime) | 8.97 MB | **3.2** | **2.0** | 96.68% | 99.15% | 0.00936 |
-| ONNX int8 (ORT dynamic, supplementary) | **2.44 MB** | 6.5 | 5.8 | 96.52% | 99.15% | 0.01108 |
-
-Findings:
-
- **torch dynamic INT8 quantizes nothing on this model.** The architecture has
-  **zero `nn.Linear` layers** — it is entirely Conv1d (21) + Conv2d (22) +
-  BatchNorm. `torch.ao.quantization.quantize_dynamic` (requested over
-  `{Linear, Conv1d, Conv2d}`) converted **0 modules / 0.0% of params**: dynamic
-  quantization only has kernels for Linear/RNN-family modules and silently
-  skips convolutions. The "int8" model is bit-identical to fp32 (same outputs,
-  same 9.07 MB). Conv quantization would require static (PTQ) quantization
-  with calibration — out of scope here; the ORT dynamic path below is the
-  honest int8 datapoint.
- **fp16 halves size for free accuracy-wise** (PCK@20 −0.005 pt, MPJPE
-  +0.0001) but is *slower* on CPU at batch 1 (~2.2×) — torch CPU fp16 conv
-  kernels are emulated. fp16 is a storage/transport format here, not a CPU
-  runtime win.
- **ONNX Runtime is the real batch-1 latency win: ~3.4× faster than torch**
-  (3.2 vs 11.0 ms/window) at identical accuracy (parity 2.4e-7).
-
-### Verdict on the paper's "~2.2 MB int8" claim
-
-**Plausible but not free, and unreachable by the obvious PyTorch route.**
-2,225,042 params × 1 byte ≈ 2.2 MB assumes *every* parameter quantizes.
-PyTorch dynamic quantization — the one-liner most readers would reach for —
-yields **9.07 MB (0% quantized)** because the model has no Linear layers.
-ONNX Runtime dynamic quantization, which does have int8 conv weight support,
-gets **2.44 MB** (close to the claim; the overhead is BatchNorm params/buffers
-and quantization scales kept in fp32) at a measurable accuracy cost:
-PCK@20 96.68 → 96.52% (−0.16 pt) and MPJPE 0.00936 → 0.01108 (+18%), and
-~2× slower inference than ONNX fp32 (ConvInteger kernels). The paper does not
-state a method or an int8 accuracy; treat "2.2 MB" as a weight-arithmetic
-estimate, achievable in practice only via conv-capable quantization toolchains
-and with a small accuracy penalty.
-
-### ONNX export status
-
-**Works.** Exported via the TorchScript exporter (`dynamo=False`), opset 17,
-with a dynamic batch axis — `results/retrained_fp32_dynamic.onnx` (8.97 MB),
-verified to run at batch 1/2/64. The axial attention's
-`view(N*W, C, H)` reshape traced correctly (sizes recorded as graph ops, not
-baked constants). The dynamo exporter also captures the graph but crashed on
-this box writing a ✅ to a cp1252 console (cosmetic Windows encoding issue, not
-a model blocker). Parity vs torch on the stored fixture
-(`results/parity_fixture.npz`, batch 2, seed 42): **max abs diff 2.4e-7 —
-PASS** (< 1e-4). ORT-quantized int8 model: `results/retrained_int8_ort_dynamic.onnx`.
-
-### Static PTQ (calibrated) — follow-up
-
-Follow-up to the dynamic-int8 row above (2026-06-10, same box, onnxruntime
-1.26.0): ONNX Runtime **static** post-training quantization
-(`quantize_static`, QDQ format, per-channel int8 weights + int8 activations)
-of the same fp32 export, calibrated on **corruption-free TRAINING-split
-windows only** (seed-42 file-level split, same masks; 1,000 windows for
-MinMax, 512 for the histogram calibrators; never test windows). Scopes:
-"conv-only" (`op_types_to_quantize=["Conv"]` — the attention path exports as
-Einsum/Softmax, which ORT never quantizes anyway, so "all-ops" additionally
-quantizes the elementwise Mul/Sigmoid/Add/AveragePool glue). Accuracy on the
-identical 10k-window seed-42 corruption-free test subset; latency median of
-3 interleaved reps (fp32/dynamic re-benched in-session as references).
-Script: `static_ptq_bench.py`; raw: `results/edge_optimization.json`
-(`onnx_static_ptq`).
-
-| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
-|---|---|---|---|---|---|---|
-| ONNX fp32 (reference) | 8.97 MB | 2.5 | 1.9 | 96.68% | 99.15% | 0.00936 |
-| ORT dynamic int8 (baseline) | **2.44 MB** | 5.7 | 4.6 | 96.52% | 99.15% | 0.01108 |
-| static QDQ **Percentile(99.99) conv-only** | 2.53 MB | 5.3 | 4.7 | 96.61% | 99.16% | **0.01031** |
-| static QDQ MinMax conv-only | 2.53 MB | 5.2 | 3.3 | **96.63%** | 99.19% | 0.01084 |
-| static QDQ Entropy conv-only | 2.53 MB | 5.2 | 3.1 | 96.60% | 99.19% | 0.01078 |
-| static QDQ MinMax all-ops | 2.60 MB | 6.5 | 3.9 | 95.45% | 99.14% | 0.01486 |
-| static QDQ Entropy all-ops | 2.60 MB | 5.7 | 4.1 | 95.30% | 99.13% | 0.01510 |
-| static QDQ Percentile all-ops | 2.60 MB | 5.3 | 4.3 | 96.39% | 99.17% | 0.01218 |
-
-**Verdict: static PTQ (conv-only) is the new best int8 point on accuracy —
-but only modestly, and it does not fix int8's latency penalty.**
-
- **Accuracy: beats dynamic.** All three conv-only calibrations land at
-  PCK@20 96.60–96.63% (vs dynamic 96.52%, fp32 96.68% — recovers ~⅔ of the
-  dynamic gap) and MPJPE 0.0103–0.0108 (vs dynamic 0.01108). Best MPJPE:
-  Percentile conv-only, +10% over fp32 instead of dynamic's +18%.
- **Size: slightly worse.** 2.53 MB vs 2.44 MB (+3.6%) — QDQ nodes and
-  per-channel scales cost a little; BatchNorm stays fp32 in both (the 12 BNs
-  follow Slice/Einsum/Reshape, never Conv, so they cannot be folded).
- **Latency: a wash vs dynamic, still ~2× slower than ONNX fp32 at batch 1.**
-  Batch-1 medians 5.2–5.3 vs dynamic 5.7 ms/win in-session — within this
-  box's ±20–40% noise. Batch 64 leans static (3.1–3.3 for MinMax/Entropy
-  conv-only vs 4.6), same caveat.
- **All-ops QDQ is strictly worse**: up to −1.4 pt PCK@20 and +60% MPJPE for
-  zero size/latency benefit — int8 activations through the elementwise glue
-  around the attention blocks is where the damage is. Conv-only is the right
-  scope.
- Negative result worth recording: **Entropy calibration is a no-op here** —
-  on an identical calibration set it selects full-range thresholds
-  bit-identical to MinMax (all 247 scales equal; verified on a 64-window
-  smoke set). Also, ORT 1.26's `CalibMaxIntermediateOutputs` raises a
-  spurious "No data is collected" when the batch count divides the chunk
-  size (worked around in the script).
-
-Deployment guidance: need speed → ONNX fp32 (3.2 ms b1). Need int8 weights
-for size → static QDQ conv-only (Percentile or MinMax,
-`results/retrained_int8_static_percentile_conv.onnx`), which strictly
-dominates dynamic int8 on accuracy at ~equal latency and +0.09 MB.
-
-## Efficiency sweep (MEASURED, overnight 2026-06-10/11)
-
-ADR-152 beyond-SOTA track: compact purpose-built variants of the WiFlow-STD
-architecture, trained from scratch on the same cleaned dataset, identical
-seed-42 file-level split, loss and protocol as the measurement-(a) reference
-(fp32, batch 64, ≤50 epochs, patience 5; RTX 5080, ~22–29 min/variant).
-Variant transforms are pure channel/group/stride scalings of an
-architecture-exact parameterized model (validated: reproduces 2,225,042 params
-at the reference config). Scripts: `remote/sweep/`; raw:
-`results/efficiency_sweep.jsonl`; checkpoints `results/{half,quarter,tiny}_best.pth`
-(gitignored).
-
-| Variant | Params | vs 2.23M | Clean-test PCK@20 | PCK@50 | MPJPE | Best epoch |
-|---|---|---|---|---|---|---|
-| full (reference, meas. a) | 2,225,042 | 1× | 96.61% | 99.11% | 0.0094 | 36 |
-| **half** | **843,834** | **0.38×** | **96.62%** | **99.47%** | **0.00898** | 23 |
-| quarter | 338,600 | 0.15× | 96.05% | 99.43% | 0.00928 | 50 |
-| tiny | 56,290 | 0.025× | 94.11% | 99.36% | 0.0125 | 47 |
-
-Findings:
-
- **The half model (843k params) strictly dominates the full reference** on
-  this dataset — equal PCK@20, better PCK@50 and MPJPE, converges in fewer
-  epochs. The published 2.23M architecture is over-parameterized for its own
-  benchmark.
- **tiny (56k params, 1/39.5) holds 94.11% PCK@20** — a ~220 KB fp32 /
-  ~60 KB int8-class model in reach of severely constrained edge targets,
-  at −2.5 pt from the full reference.
- Caveats: in-domain (5-subject random-file split) like every number on this
-  dataset; single run per variant; corruption-free test subset (52,560).
-  Cross-domain behavior of compact variants is untested — ADR-150's evidence
-  says capacity *hurts* cross-subject, so the compact end may generalize no
-  worse, but that is a hypothesis, not a measurement.
-
-### Compact-variant edge artifacts (MEASURED, 2026-06-11)
-
-Edge pipeline for the **tiny** checkpoint (56,290 params), same machinery and
-protocol as the full-model edge rows above (this Windows box, torch
-2.12.0+cpu, onnxruntime 1.26.0; dynamic-batch opset-17 TorchScript export;
-static QDQ **Percentile(99.99) conv-only** int8 calibrated on **512**
-corruption-free TRAIN-split windows; accuracy on the identical 10k-window
-seed-42 clean test subset; latency = median ms/window over 3 interleaved
-reps, with the full-model fp32/int8 sessions interleaved as same-session
-references). Script: `tiny_edge_bench.py`; raw:
-`results/edge_optimization.json` (`tiny_variant`). Torch-vs-ORT parity on the
-stored fixture input: **max abs diff 1.5e-7 — PASS** (< 1e-4). The tiny fp32
-subset PCK@20 (94.11%) matches the full clean-test sweep figure (94.11%)
-exactly, so the subset remains representative.
-
-Two forced deviations, both recorded in the JSON:
-
-1. **Adaptive-pool export rewrite.** tiny's derived stride schedule
-   `[2,1,1,1]` leaves feature width 16, and the TorchScript exporter rejects
-   `AdaptiveAvgPool2d((15,1))` when 15 is not a factor of the input height
-   (the full model never hit this — its width was exactly 15). Since the
-   pool over a fixed-size map is a fixed linear operator, the export wrapper
-   replaces it with `mean(-1)` (W axis, a factor) + a constant averaging
-   matmul using PyTorch's exact bin rule; the parity check (vs the original
-   torch model with the real pool) proves exactness.
-2. **Calibration count 512, not "~500"**: ORT 1.26's histogram collector
-   `np.asarray()`'s the per-batch maxima, so the calibration count must be a
-   multiple of the 64-window calibration batch or the ragged last batch
-   crashes it (the earlier static-PTQ run dodged this by using exactly 512).
-
-| Variant | Disk size | Batch 1 (ms/win) | Batch 64 (ms/win) | PCK@20 | PCK@50 | MPJPE |
-|---|---|---|---|---|---|---|
-| full ONNX fp32 (same-session ref) | 8.97 MB | 2.27 | 1.42 | 96.68% | 99.15% | 0.00936 |
-| full static QDQ Percentile conv-only (same-session ref) | 2.53 MB | 5.53 | 3.82 | 96.61% | 99.16% | 0.01031 |
-| **tiny ONNX fp32** | **0.295 MB** | **0.66** | **0.24** | **94.11%** | 99.37% | 0.01253 |
-| tiny static QDQ Percentile conv-only | 0.248 MB | 0.85 | 1.03 | 92.68% | 99.33% | 0.01491 |
-
-(tiny torch `.pth` checkpoint for reference: 0.34 MB on disk; 56,290 fp32
-params ≈ 225 KB of weights.)
-
-Findings:
-
- **The smallest deployable WiFlow-class model is the tiny ONNX fp32
-  artifact: ~295 KB on disk, 0.66 ms/window batch-1 CPU (~1,500 windows/s),
-  94.1% PCK@20** — 30× smaller and ~3.4× faster (in-session) than the full
-  ONNX fp32 model for −2.6 pt PCK@20.
- **int8 is a bad trade at this scale.** Static QDQ conv-only — the recipe
-  that cost the full model only 0.07 pt — costs tiny **−1.43 pt** PCK@20
-  (94.11 → 92.68%) and +19% MPJPE, saves only 47 KB (−16%; QDQ scales and
-  the fp32 BN/attention glue are proportionally larger in a small graph),
-  and is *slower* than tiny fp32 (0.85 vs 0.66 ms b1; 1.03 vs 0.24 ms b64 —
-  QDQ kernel overhead dominates when the convs are this small). A 56k-param
-  model has little redundancy left to absorb weight+activation rounding.
- Deployment guidance, compact edition: ship tiny as **ONNX fp32** — at
-  295 KB the int8 size saving solves no real constraint and costs accuracy
-  and speed. If ~250 KB vs ~295 KB ever matters, weight-only quantization
-  would be the thing to try next, not QDQ.
-
-## Measurement (b): BLOCKED-ON-DATA (attempted 2026-06-10)
-
-The fine-tune-on-ESP32 measurement stopped at dataset characterization, per the
-pre-registered stop rule (<2,000 paired windows). Findings (MEASURED):
-
- **Only one trainable paired dataset exists**: `ruvultra:~/work/cog-pose-train/paired.jsonl`
-  — 1,077 windows (one subject, one room, one 29.9-min session, single node;
-  CSI [56, 20]; 17 COCO keypoints, MediaPipe confidence mean 0.44 — only 264
-  windows pass ADR-079's own conf>0.5 training filter). Prior measured attempts
-  on this exact set: 0–3% torso-PCK@20 (temporal splits, three independent
-  pipelines). Fine-tuning a 2.23M-param model on ~860 train windows would
-  measure memorization, not transfer.
- **The April session behind the old "92.9% PCK@20" claim is lost** (345
-  samples, 35 subcarriers; raw CSI gone from ruvzen/ruvultra/cognitum-v0; only
-  a 69-sample predictions+GT holdout survives at `models/wiflow-real/eval-holdout.jsonl`).
- **Forensic recheck of that holdout RETRACTS the 92.9% figure**: the trainer's
-  `pck()` used an absolute 0.2 image-unit threshold (not torso-normalized) and
-  the model output a **constant pose** (pred std 0.0000 across 69 near-static
-  frames; a mean predictor scores 100% under the same protocol). The
-  torso-normalized PCK@20 on the same holdout is 19.1%. This corroborates the
-  2026-05-11 audit retraction (CHANGELOG, PR #535); stale doc citations were
-  removed 2026-06-10 (user-guide, readme-details, ADR-152 §2.1.3). The §2.2
-  no-citation rule now applies to ADR-079 accuracy claims.
-
-Unblock criteria: a paired collection session of ≥2k windows (≈35+ min at the
-observed stride; multi-pose, conf>0.5, ideally with the §2.1.3 two-checkerboard
-calibration), plus a re-baselined our-pipeline number under torso-PCK@20 on the
-same split. WiFlow-STD assets stand ready on ruvultra (`~/wiflow-std-bench/`).
-Also worth investigating: ADR-079's protocol predicts ~9k windows per 30 min;
-the May session under-delivered ~8× (aligner drop rate?).
-
-## Measurement (b) (MEASURED 2026-06-10/11)
-
-The data baseline unblocked: the 2026-06-10 22:10–22:40 collection session produced
-**2,046 paired windows** (`ruvultra:~/wiflow-std-bench/paired-20260610.jsonl`; ONE
-subject, ONE room, ONE ESP32 node, varied poses: walk/raise/squat/kick/wave/turn/
-jump/sit; aligner `scripts/align-ground-truth.js`, non-overlapping 20-frame windows
-~0.42 s; 17 COCO keypoints in normalized [0,1] camera coords; MediaPipe confidence
-mean 0.802, min 0.692 — all windows pass the conf>0.5 filter). The −4 h timestamp
-bug and the empty-frame confidence-dilution aligner findings are recorded
-separately; results only here. Trained on ruvultra (RTX 5080, torch 2.11+cu128,
-fp32, batch 32, GPU shared with the efficiency sweep). Scripts mirrored in
-`remote/measb/`; raw metrics + full training curves in `results/measurement_b.json`.
-
-### Two new aligner/dataset findings (forced deviations, MEASURED)
-
-1. **`csi_shape` is heterogeneous, not [70, 20]**: 1,347× [70,20], 284× [134,20],
-   243× [26,20], 130× [12,20], 42× [20,20]. The ESP32 stream emits mixed frame
-   types and `extractCsiMatrix` stamps each window's subcarrier count from
-   `window[0].subcarriers`, zero-padding/truncating the other frames — even
-   native-70 windows contain ~20.4% internally zero-padded short frames
-   (subcarriers 40–69 all-zero). Handling: the primary suite ("all 2,046")
-   linearly resamples every frame's subcarrier axis to 70 bins (identity for
-   native-70 frames) so the pre-registered n and split sizes hold; a secondary
-   suite restricts to the 1,347 native [70,20] windows as a homogeneity check.
-2. **Aligner layout bug**: `extractCsiMatrix` fills `matrix[f * nSc + s]`
-   (frame-major) but declares `shape: [nSc, nFrames]` — the stored shape label is
-   transposed relative to the data. Confirmed by coherent per-frame zero-tails;
-   corrected on load (`reshape(nFrames, nSc).T`).
-
-### Protocol (pre-registered, followed)
-
-Temporal split, no shuffling across time: first 70% train (1,432), next 15% val
-(307), last 15% test (307); seed 42 elsewhere. Model: learned 1×1 Conv1d 70→540
-adapter prepended to the upstream WiFlow-STD trunk; K=17 via the parameter-free
-adaptive pool (`AdaptiveAvgPool2d((17,1))` — pretrained weights load strict for
-any K). CSI normalized by the TRAIN-split p99 amplitude (129.7 all / 130.9
-native-70), clipped to [0,1]. Three runs, ≤60 epochs, early-stop patience 8 on
-val MPJPE, AdamW (adapter lr 1e-4; pretrained trunk lr 1e-5, 10× lower; scratch
-all 1e-4), fp32. Pretrained init = the measurement-(a) **retrained** checkpoint
-(`upstream/test/best_pose_model.pth`, ~96% PCK@20 on WiFlow data; the
-`att.`/`final_conv.` key remap from `eval_repro.py` applied defensively — a no-op,
-that checkpoint already uses post-rename keys). Frozen-trunk run: trunk
-`requires_grad=False` **and** held in `.eval()` so BatchNorm running stats cannot
-drift — a pure transfer probe; only the 70→540 adapter (38,340 params) trains.
-
-PCK is torso-normalized with **torso = ‖l_shoulder(5) − l_hip(11)‖** (upstream
-`calculate_pck` math — per-frame norm clamped at 0.01, mean over keypoints ×
-frames — but upstream's `NECK_IDX/PELVIS_IDX = 2, 12` is a 15-keypoint
-convention; on 17-kp COCO those indices are right_eye/right_hip, so the indices
-were replaced, not the math). MPJPE is in normalized image units (not meters).
-
-### Results — primary suite, all 2,046 windows (test = last 307)
-
-| Run | PCK@10 | PCK@20 | PCK@30 | PCK@40 | PCK@50 | MPJPE | pred std | best ep |
-|---|---|---|---|---|---|---|---|---|
-| **mean-pose baseline** (honesty bar) | **73.1%** | **95.9%** | **98.7%** | 99.3% | 99.3% | **0.0148** | 0 (by constr.) | — |
-| (i) pretrained-init, full fine-tune | 26.0% | 65.0% | 88.0% | 96.4% | 98.9% | 0.0313 | 0.0113 | 58/60 |
-| (ii) scratch | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.2554 | 0.0002 | 4 (stop @13) |
-| (iii) frozen-trunk (adapter only) | 0.0% | 0.0% | 0.2% | 3.2% | 14.4% | 0.1260 | 0.0073 | 59/60 |
-
-Secondary suite (native [70,20] windows only, n=1,347, test=202) reproduces the
-same ordering: mean-baseline 96.0% / pretrained 67.1% / scratch 0.0% /
-frozen-trunk 0.0% PCK@20 (MPJPE 0.0153 / 0.0318 / 0.2236 / 0.1343) — the
-subcarrier-resampling choice does not change any conclusion.
-
-### Interpretation
-
- **Did pretraining-transfer happen? Partially — as optimization transfer, not
-  feature transfer, and not past the honesty bar.**
-  - *Pretrained vs scratch*: dramatic (65.0% vs 0.0% PCK@20). The pretrained init
-    is the only configuration that trains at all under the pre-registered budget.
-  - *Frozen-trunk*: near-zero (0.0% PCK@20, 14.4% @50). WiFlow-STD's frozen
-    features do **not** transfer to our ESP32 domain through a linear subcarrier
-    adapter — the pretrained benefit is a well-conditioned initialization (incl.
-    calibrated BN/output scales), not reusable CSI→pose features.
-  - *Everything vs mean-pose baseline*: **no run beats it.** A constant
-    train-mean pose scores 95.9% torso-PCK@20 / 0.0148 MPJPE on this test split,
-    because a single subject in one camera frame barely moves in normalized
-    coordinates. The fine-tuned model is a real, non-constant model
-    (pred std 0.0113 > 0 — passes the constant-pose detector that retracted the
-    old 92.9% figure) but its deviations from the mean hurt: it fits train-period
-    temporal dynamics that do not generalize across the temporal split.
- **Verdict for ADR-152 §2.2(b): fine-tuning WiFlow-STD on this dataset does not
-  demonstrate CSI→pose signal beyond the mean pose.** Until a model beats the
-  mean-pose baseline on a temporal split, no PCK number from this line may be
-  cited as pose-estimation capability.
-
-### Caveats (honest, pre-registered)
-
- Single subject, single room, single session (30 min), single ESP32 node —
-  in-domain temporal split only; nothing here speaks to cross-room or
-  cross-subject generalization.
- 2k windows vs the 360k-window WiFlow-STD corpus — **NOT comparable** to the
-  ~96% in-domain measurement-(a) number, and the published 97.25% even less so.
- The scratch run's total collapse (it cannot even reach the mean pose; its
-  output BatchNorm/SiLU head must learn output scale from random init at lr 1e-4)
-  is an optimization outcome under the fixed budget, not proof the architecture
-  cannot learn from scratch — the pretrained-vs-scratch gap partially reflects
-  this conditioning advantage.
- Mixed-subcarrier frames (finding 1) mean even the "clean" windows carry ~20%
-  zero-padded frames; collection-side frame-type filtering should precede the
-  next session.
- Mean-baseline PCK is inflated by low pose variance relative to torso size
-  (~0.2–0.3 image units); PCK@10 (73.1%) shows the same ceiling effect at a
-  stricter threshold — the bar is the bar, but a livelier dataset would lower it.
-
-## Pending
-
- (b) fine-tune on our ESP32 17-keypoint eval set — **MEASURED 2026-06-10/11**,
-  see above: no run beats the mean-pose baseline; pretraining transfers as
-  optimization aid only.
- (c) our internal WiFlow on their dataset (15-keypoint subset mapping) — also
-  affected: there is currently no validated internal pose model to compare
-  (the 92.9% artifact is retracted; the MM-Fi SOTA models in ADR-150 §3 are a
-  different input domain).
@@ -1,200 +0,0 @@
-"""Shared infrastructure for the LOCAL wiflow-std benchmark scripts (ADR-152).
-
-This module is the single canonical implementation of the helpers that were
-previously copy-pasted across eval_repro.py / quantize_bench.py /
-onnx_bench.py / eval_ort_accuracy.py / export_to_safetensors.py:
-
-  - ``import_upstream()``  -- sys.path setup + the models-package stub that
-    works around the upstream import bug, plus the >1GB np.load mmap patch
-  - ``install_np_load_mmap_patch()`` -- the mmap patch on its own
-  - ``remap_legacy_keys()`` / ``load_remapped_state()`` -- checkpoint
-    key remap for the pre-rename released checkpoint
-  - ``load_wiflow_model()`` -- WiFlowPoseModel from a checkpoint, eval mode
-  - ``set_seed()`` -- mirrors upstream run.py seeding exactly
-  - ``evaluate()`` -- THE canonical batch-weighted PCK/MPJPE evaluation loop
-    (thresholds 0.1-0.5, upstream utils/metrics.py math); accepts either a
-    torch nn.Module or an onnxruntime InferenceSession
-
-The scripts under remote/ deploy to ruvultra as standalone single files and
-therefore intentionally inline private copies of these helpers; when editing
-them, treat this module as the reference implementation and keep the copies
-in sync.
-"""
-
-import os
-import random
-import sys
-import time
-import types
-
-import numpy as np
-import torch
-
-HERE = os.path.dirname(os.path.abspath(__file__))
-UPSTREAM = os.path.join(HERE, "upstream")
-RESULTS = os.path.join(HERE, "results")
-
-DEFAULT_THRESHOLDS = (0.1, 0.2, 0.3, 0.4, 0.5)
-
-# ---------------------------------------------------------------------------
-# >1GB np.load mmap patch
-# ---------------------------------------------------------------------------
-
-# csi_windows.npy is ~13 GB; mmap large arrays instead of loading into RAM
-# (loading it eagerly needs ~15 GB).
-_np_load = np.load
-
-
-def _np_load_mmap(path, *a, **kw):
-    if (isinstance(path, str) and path.endswith(".npy")
-            and os.path.getsize(path) > 1 << 30 and "mmap_mode" not in kw):
-        kw["mmap_mode"] = "r"
-    return _np_load(path, *a, **kw)
-
-
-def install_np_load_mmap_patch():
-    """Globally patch np.load so .npy files >1GB are mmap'd read-only.
-
-    Idempotent. Patching the numpy module attribute is equivalent to the
-    historical ``upstream_dataset.np.load = _np_load_mmap`` (dataset.np IS
-    the numpy module), but works regardless of import order.
-    """
-    np.load = _np_load_mmap
-
-
-# ---------------------------------------------------------------------------
-# upstream import shim
-# ---------------------------------------------------------------------------
-
-def import_upstream(mmap_patch=True):
-    """Make the upstream WiFlow-STD clone importable; returns its path.
-
-    Upstream bug: models/__init__.py imports TemporalConvNet, which
-    models/tcn.py does not define -- the package fails to import as
-    published. Register a stub package so the broken __init__ never
-    executes; submodules (models.pose_model etc.) still resolve via
-    __path__. Idempotent.
-    """
-    if UPSTREAM not in sys.path:
-        sys.path.insert(0, UPSTREAM)
-    if "models" not in sys.modules:
-        _models_pkg = types.ModuleType("models")
-        _models_pkg.__path__ = [os.path.join(UPSTREAM, "models")]
-        sys.modules["models"] = _models_pkg
-    if mmap_patch:
-        install_np_load_mmap_patch()
-    return UPSTREAM
-
-
-# ---------------------------------------------------------------------------
-# checkpoint loading
-# ---------------------------------------------------------------------------
-
-# The released checkpoint predates the published code: modules were renamed
-# att -> attention, final_conv -> decoder (param count identical, 2.23M).
-LEGACY_RENAMES = {"att.": "attention.", "final_conv.": "decoder."}
-
-
-def remap_legacy_keys(state):
-    """Remap pre-rename state_dict keys; no-op for already-new-style keys."""
-    return {next((new + k[len(old):] for old, new in LEGACY_RENAMES.items()
-                  if k.startswith(old)), k): v
-            for k, v in state.items()}
-
-
-def load_remapped_state(path, map_location="cpu"):
-    """torch.load (weights_only) + legacy key remap."""
-    state = torch.load(path, map_location=map_location, weights_only=True)
-    return remap_legacy_keys(state)
-
-
-def load_wiflow_model(checkpoint, map_location="cpu", dropout=0.5):
-    """Full-size WiFlowPoseModel from a checkpoint, strict load, eval mode."""
-    import_upstream()
-    from models.pose_model import WiFlowPoseModel
-    model = WiFlowPoseModel(dropout=dropout)
-    model.load_state_dict(load_remapped_state(checkpoint, map_location),
-                          strict=True)
-    model.eval()
-    return model
-
-
-# ---------------------------------------------------------------------------
-# seeding
-# ---------------------------------------------------------------------------
-
-def set_seed(seed=42):
-    # mirror upstream run.py exactly
-    random.seed(seed)
-    np.random.seed(seed)
-    torch.manual_seed(seed)
-    if torch.cuda.is_available():
-        torch.cuda.manual_seed(seed)
-        torch.cuda.manual_seed_all(seed)
-    torch.backends.cudnn.deterministic = True
-    torch.backends.cudnn.benchmark = False
-
-
-# ---------------------------------------------------------------------------
-# THE canonical evaluation loop
-# ---------------------------------------------------------------------------
-
-def evaluate(model, loader, device=None, dtype=None, label="",
-             thresholds=DEFAULT_THRESHOLDS, progress_every=50):
-    """Batch-weighted PCK/MPJPE over a DataLoader (upstream metrics math).
-
-    ``model`` may be a torch nn.Module (optionally evaluated on ``device``
-    with inputs cast to ``dtype``) or an onnxruntime InferenceSession.
-    Per-threshold PCK values are independent in upstream calculate_pck, so
-    evaluating a superset of thresholds never changes any individual value.
-
-    Returns {"samples", "mpjpe", "pck@10".."pck@50", "wall_seconds"}.
-    """
-    import_upstream()
-    from utils.metrics import calculate_mpjpe, calculate_pck
-
-    is_ort = hasattr(model, "get_inputs")  # onnxruntime InferenceSession
-    if is_ort:
-        inp = model.get_inputs()[0].name
-
-        def forward(bx):
-            return torch.from_numpy(model.run(None, {inp: bx.numpy()})[0])
-    else:
-        model.eval()
-
-        def forward(bx):
-            if device is not None:
-                bx = bx.to(device)
-            if dtype is not None:
-                bx = bx.to(dtype)
-            return model(bx).float()
-
-    thresholds = list(thresholds)
-    totals = {t: 0.0 for t in thresholds}
-    total_mpe, n = 0.0, 0
-    t0 = time.time()
-    with torch.no_grad():
-        for batch_idx, (bx, by) in enumerate(loader):
-            out = forward(bx)
-            if device is not None and not is_ort:
-                by = by.to(device)
-            mpe = calculate_mpjpe(out, by)
-            pck = calculate_pck(out, by, thresholds=thresholds)
-            bs = by.size(0)
-            total_mpe += mpe * bs
-            for t in totals:
-                totals[t] += pck[t] * bs
-            n += bs
-            if batch_idx % progress_every == 0:
-                tag = f"[{label}] " if label else ""
-                pck20 = totals.get(0.2)
-                pck20_str = f"pck20={pck20 / n:.4f} " if pck20 is not None else ""
-                print(f"  {tag}batch {batch_idx}: n={n} {pck20_str}"
-                      f"mpjpe={total_mpe / n:.4f} ({time.time() - t0:.0f}s)",
-                      flush=True)
-    return {
-        "samples": n,
-        "mpjpe": total_mpe / n,
-        **{f"pck@{int(t * 100)}": totals[t] / n for t in thresholds},
-        "wall_seconds": time.time() - t0,
-    }
@@ -1,67 +0,0 @@
-"""ADR-152 edge optimization: accuracy of the ONNX fp32 and ORT-dynamic-int8
-models on the same corruption-free 10k test subset used by quantize_bench.py.
-
-The torch dynamic-int8 path quantizes nothing (no nn.Linear in the model), so
-the only real int8 datapoint for the paper's "~2.2 MB int8" claim is the
-onnxruntime dynamically quantized model -- this script measures what that
-quantization costs in PCK/MPJPE.
-
-Usage:
-  .venv/Scripts/python.exe eval_ort_accuracy.py \
-      --data-dir <preprocessed_csi_data> [--subset 10000]
-
-Writes/merges into results/edge_optimization.json under key "onnx_accuracy".
-"""
-
-import argparse
-import json
-import os
-import sys
-
-HERE = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, HERE)
-
-from _bench_common import RESULTS, evaluate  # noqa: E402
-from quantize_bench import build_test_subset  # noqa: E402  (sets up upstream imports)
-
-
-def evaluate_ort(sess, loader, label):
-    """ORT-session evaluation via the canonical _bench_common.evaluate loop."""
-    return evaluate(sess, loader, label=label)
-
-
-def main():
-    import onnxruntime as ort
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--data-dir", default=os.path.join(
-        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
-        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
-    parser.add_argument("--subset", type=int, default=10000)
-    parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
-    args = parser.parse_args()
-
-    loader, _n_clean = build_test_subset(args.data_dir, args.subset)
-    results = {}
-    for label, fname in (("onnx_fp32", "retrained_fp32_dynamic.onnx"),
-                         ("onnx_int8_ort_dynamic", "retrained_int8_ort_dynamic.onnx")):
-        path = os.path.join(RESULTS, fname)
-        if not os.path.exists(path):
-            results[label] = {"error": f"{fname} not found; run onnx_bench.py first"}
-            continue
-        sess = ort.InferenceSession(path, providers=["CPUExecutionProvider"])
-        print(f"=== accuracy: {label} ({fname}) ===")
-        results[label] = evaluate_ort(sess, loader, label)
-        print(json.dumps(results[label], indent=2))
-
-    merged = {}
-    if os.path.exists(args.out):
-        with open(args.out) as f:
-            merged = json.load(f)
-    merged["onnx_accuracy"] = results
-    with open(args.out, "w") as f:
-        json.dump(merged, f, indent=2)
-    print(f"wrote {args.out}")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,102 +0,0 @@
-"""ADR-152 §2.2 measurement (a): reproduce WiFlow-STD (DY2434) published test metrics.
-
-Runs the released pretrained checkpoint (upstream/best_pose_model.pth) against the
-released Kaggle dataset (kaka2434/wiflow-dataset) using the upstream code path:
-identical dataset class, identical file-level 70/15/15 split at seed 42, identical
-PCK/MPJPE implementations (utils/metrics.py).
-
-Published claims (README, "Setting 1 random split"):
-  PCK@20 97.25% | PCK@30 98.63% | PCK@40 99.16% | PCK@50 99.48% | MPJPE 0.007 m
-
-Usage:
-  .venv/Scripts/python.exe eval_repro.py --data-dir <dir containing csi_windows.npy>
-"""
-
-import argparse
-import json
-import os
-import sys
-
-import torch
-from torch.utils.data import DataLoader
-
-from _bench_common import (UPSTREAM, evaluate, import_upstream,
-                           load_remapped_state, set_seed)
-
-import_upstream()  # sys.path + models stub + >1GB np.load mmap patch
-
-from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders  # noqa: E402
-from models.pose_model import WiFlowPoseModel  # noqa: E402
-
-
-def find_data_dir(root):
-    for dirpath, _dirnames, filenames in os.walk(root):
-        if "csi_windows.npy" in filenames:
-            return dirpath
-    return None
-
-
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--data-dir", required=True,
-                        help="Directory containing csi_windows.npy (searched recursively)")
-    parser.add_argument("--checkpoint", default=os.path.join(UPSTREAM, "best_pose_model.pth"))
-    parser.add_argument("--batch-size", type=int, default=64)
-    parser.add_argument("--out", default=os.path.join(os.path.dirname(os.path.abspath(__file__)),
-                                                      "results", "repro_a.json"))
-    args = parser.parse_args()
-
-    data_dir = args.data_dir
-    if not os.path.exists(os.path.join(data_dir, "csi_windows.npy")):
-        located = find_data_dir(data_dir)
-        if located is None:
-            sys.exit(f"csi_windows.npy not found under {data_dir}")
-        data_dir = located
-    print(f"data dir: {data_dir}")
-
-    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-    print(f"device: {device}, torch {torch.__version__}")
-
-    set_seed(42)
-
-    dataset = PreprocessedCSIKeypointsDataset(
-        data_dir=data_dir, keypoint_scale=1000.0, enable_temporal_clean=True)
-
-    # split must match upstream: file-level shuffle at random_seed=42, 70/15/15
-    _train_loader, _val_loader, test_loader = create_preprocessed_train_val_test_loaders(
-        dataset=dataset, batch_size=args.batch_size, num_workers=0, random_seed=42)
-
-    model = WiFlowPoseModel(dropout=0.5).to(device)
-    # released checkpoint predates the published code: modules were renamed
-    # att -> attention, final_conv -> decoder (param count identical, 2.23M)
-    state = load_remapped_state(args.checkpoint, map_location=device)
-    model.load_state_dict(state, strict=True)
-    n_params = sum(p.numel() for p in model.parameters())
-    print(f"checkpoint: {args.checkpoint} ({n_params/1e6:.2f}M params)")
-
-    # upstream also evaluates with drop_last=True; we report the full test set
-    # (drop_last=False) and the drop_last variant for exact comparability
-    results = {"published": {"pck@20": 0.9725, "pck@30": 0.9863, "pck@40": 0.9916,
-                             "pck@50": 0.9948, "mpjpe": 0.007},
-               "params_millions": n_params / 1e6,
-               "data_dir": data_dir,
-               "device": str(device)}
-
-    print("=== test set (full, drop_last=False) ===")
-    results["test_full"] = evaluate(model, test_loader, device=device)
-    print(json.dumps(results["test_full"], indent=2))
-
-    test_loader_dl = DataLoader(test_loader.dataset, batch_size=args.batch_size,
-                                shuffle=False, drop_last=True)
-    print("=== test set (drop_last=True, as upstream train.py) ===")
-    results["test_drop_last"] = evaluate(model, test_loader_dl, device=device)
-    print(json.dumps(results["test_drop_last"], indent=2))
-
-    os.makedirs(os.path.dirname(args.out), exist_ok=True)
-    with open(args.out, "w") as f:
-        json.dump(results, f, indent=2)
-    print(f"wrote {args.out}")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,174 +0,0 @@
-"""ADR-152 §2.2: export the retrained WiFlow-STD PyTorch checkpoint to
-safetensors with tch-rs (VarStore) variable names, plus a numerical-parity
-fixture for the Rust port.
-
-Outputs (all under results/, gitignored):
-  retrained_wiflow_std.safetensors  -- 248 f32 tensors named exactly as the
-                                       Rust WiFlowStdModel VarStore expects
-                                       (see wiflow_std/model.rs
-                                       `dump_variable_names` for the
-                                       authoritative name dump)
-  parity_fixture.npz                -- deterministic input (seed 42,
-                                       shape (2, 540, 20), uniform [0,1]) and
-                                       the Python model's eval-mode output
-  parity_fixture.json               -- same data as flattened f32 lists, for
-                                       the dependency-free Rust test
-                                       (tests/test_wiflow_std_parity.rs)
-
-PyTorch -> tch key mapping (derived from the VarStore dump, not guessed):
-
-  tcn.network.{i}.conv1_group.weight        -> tcn{i}.conv1_group.weight
-  tcn.network.{i}.bn*_{group,pw}.<leaf>     -> tcn{i}.bn*_{group,pw}.<leaf>
-  tcn.network.{i}.downsample.0.weight       -> tcn{i}.ds_conv.weight
-  tcn.network.{i}.downsample.1.<leaf>       -> tcn{i}.ds_bn.<leaf>
-  up.block.{0,1,4,5,8,9}.<leaf>             -> conv_in.{conv1,bn1,conv2,bn2,conv3,bn3}.<leaf>
-  up.downsample.{0,1}.<leaf>                -> conv_in.{ds_conv,ds_bn}.<leaf>
-  residual_blocks.{i}.block.{...}.<leaf>    -> conv{i}.{conv1..bn3}.<leaf>
-  residual_blocks.{i}.downsample.{0,1}      -> conv{i}.{ds_conv,ds_bn}
-  attention.{width,height}_axis.qkv_transform.weight
-                                            -> attention.{width,height}.qkv.weight
-  attention.{width,height}_axis.bn_*        -> attention.{width,height}.bn_*
-  decoder.{0,1,3,4}.<leaf>                  -> {dec_conv1,dec_bn1,dec_conv2,dec_bn2}.<leaf>
-  *.num_batches_tracked                     -> dropped (tch BatchNorm has no such buffer)
-
-Legacy upstream names (att. -> attention., final_conv. -> decoder.) are
-remapped first, exactly as eval_repro.py does for the released checkpoint.
-
-Usage:
-  .venv/Scripts/python.exe export_to_safetensors.py
-"""
-
-import json
-import os
-import re
-
-import numpy as np
-import torch
-from safetensors.torch import save_file
-
-from _bench_common import RESULTS, import_upstream, remap_legacy_keys
-
-import_upstream()  # sys.path + models stub
-
-from models.pose_model import WiFlowPoseModel  # noqa: E402
-
-CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
-
-# Sequential index -> tch sub-name inside one ConvBlock1/AsymmetricConvBlock:
-# [Conv2d(0), BN(1), SiLU(2), Dropout2d(3), Conv2d(4), BN(5), SiLU(6),
-#  Dropout2d(7), Conv2d(8), BN(9)]
-_BLOCK_IDX = {"0": "conv1", "1": "bn1", "4": "conv2", "5": "bn2",
-              "8": "conv3", "9": "bn3"}
-_DS_IDX = {"0": "ds_conv", "1": "ds_bn"}
-_DECODER_IDX = {"0": "dec_conv1", "1": "dec_bn1", "3": "dec_conv2",
-                "4": "dec_bn2"}
-
-
-def _conv_block(new_prefix: str, rest: str) -> str:
-    m = re.fullmatch(r"block\.(\d+)\.(.+)", rest)
-    if m:
-        return f"{new_prefix}.{_BLOCK_IDX[m.group(1)]}.{m.group(2)}"
-    m = re.fullmatch(r"downsample\.(\d+)\.(.+)", rest)
-    if m:
-        return f"{new_prefix}.{_DS_IDX[m.group(1)]}.{m.group(2)}"
-    raise KeyError(f"unmapped conv-block key: {new_prefix} / {rest}")
-
-
-def map_key(key: str) -> str:
-    """Map one PyTorch state_dict key to the tch VarStore name."""
-    m = re.fullmatch(r"tcn\.network\.(\d+)\.(.+)", key)
-    if m:
-        i, rest = m.groups()
-        rest = (rest.replace("downsample.0.", "ds_conv.")
-                    .replace("downsample.1.", "ds_bn."))
-        return f"tcn{i}.{rest}"
-
-    m = re.fullmatch(r"up\.(.+)", key)
-    if m:
-        return _conv_block("conv_in", m.group(1))
-
-    m = re.fullmatch(r"residual_blocks\.(\d+)\.(.+)", key)
-    if m:
-        return _conv_block(f"conv{m.group(1)}", m.group(2))
-
-    m = re.fullmatch(r"attention\.(width|height)_axis\.(.+)", key)
-    if m:
-        axis, rest = m.groups()
-        rest = rest.replace("qkv_transform.", "qkv.")
-        return f"attention.{axis}.{rest}"
-
-    m = re.fullmatch(r"decoder\.(\d+)\.(.+)", key)
-    if m:
-        return f"{_DECODER_IDX[m.group(1)]}.{m.group(2)}"
-
-    raise KeyError(f"unmapped checkpoint key: {key}")
-
-
-def main():
-    state = torch.load(CHECKPOINT, map_location="cpu", weights_only=True)
-    if not isinstance(state, dict) or "tcn.network.0.conv1_group.weight" not in {
-        k for k in state
-    } | {k.replace("att.", "attention.") for k in state}:
-        # tolerate trainer wrappers like {"model_state_dict": ...}
-        for wrapper in ("model_state_dict", "state_dict", "model"):
-            if isinstance(state, dict) and wrapper in state:
-                state = state[wrapper]
-                break
-
-    # Legacy upstream names predate the published code (_bench_common).
-    state = remap_legacy_keys(state)
-
-    mapped = {}
-    dropped = 0
-    for k, v in state.items():
-        if k.endswith("num_batches_tracked"):
-            dropped += 1
-            continue
-        tch_key = map_key(k)
-        if tch_key in mapped:
-            raise KeyError(f"duplicate mapped key: {k} -> {tch_key}")
-        mapped[tch_key] = v.detach().to(torch.float32).contiguous()
-
-    n_params = sum(v.numel() for k, v in mapped.items()
-                   if "running_" not in k)
-    print(f"checkpoint tensors: {len(state)} "
-          f"(dropped {dropped} num_batches_tracked)")
-    print(f"mapped tensors: {len(mapped)}, "
-          f"non-buffer params: {n_params/1e6:.6f}M")
-    assert len(mapped) == 248, f"expected 248 tch variables, got {len(mapped)}"
-    assert n_params == 2_225_042, f"param count mismatch: {n_params}"
-
-    st_path = os.path.join(RESULTS, "retrained_wiflow_std.safetensors")
-    save_file(mapped, st_path)
-    print(f"wrote {st_path}")
-
-    # ---- parity fixture --------------------------------------------------
-    model = WiFlowPoseModel(dropout=0.5)
-    model.load_state_dict(state, strict=True)
-    model.eval()
-
-    gen = torch.Generator().manual_seed(42)
-    x = torch.rand(2, 540, 20, generator=gen, dtype=torch.float32)
-    with torch.no_grad():
-        y = model(x)
-    print(f"fixture input {tuple(x.shape)} -> output {tuple(y.shape)}, "
-          f"output range [{y.min().item():.6f}, {y.max().item():.6f}]")
-
-    np.savez(os.path.join(RESULTS, "parity_fixture.npz"),
-             input=x.numpy(), output=y.numpy())
-    fixture = {
-        "seed": 42,
-        "input_shape": list(x.shape),
-        "input": x.flatten().tolist(),
-        "output_shape": list(y.shape),
-        "output": y.flatten().tolist(),
-    }
-    json_path = os.path.join(RESULTS, "parity_fixture.json")
-    with open(json_path, "w") as f:
-        json.dump(fixture, f)
-    print(f"wrote {os.path.join(RESULTS, 'parity_fixture.npz')}")
-    print(f"wrote {json_path}")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,148 +0,0 @@
-"""Regenerate results/nan_windows_mask.npy + results/big_windows_mask.npy by
-scanning a PRISTINE kagglehub download of the WiFlow-STD dataset
-(kaka2434/wiflow-dataset v1, csi_windows.npy, 360,000 windows of 540x20).
-
-============================ READ THIS FIRST ===============================
-This script MUST be run against an UNCLEANED copy of the dataset.
-
-remote/clean_v2.py (and its predecessor clean_nan.py) repair the dataset by
-zeroing the corrupted windows IN PLACE, with no backup. A cleaned copy
-contains no non-finite values and no out-of-range amplitudes, so on a cleaned
-copy this scan produces ALL-FALSE masks -- silently wrong ground truth. The
-script errors out loudly in that case (see the sanity check in main()).
-
-That irreversibility is exactly why the two committed mask files under
-results/ (gitignore-negated) are the canonical ground truth: once a download
-has been cleaned, the masks can NEVER be regenerated from it. Only run this
-on a fresh `kagglehub.dataset_download("kaka2434/wiflow-dataset")`.
-============================================================================
-
-Criteria (per window; mirrors the original 2026-06-10 scan and the
-remote/clean_v2.py repair criteria):
-
-  nan mask: any non-finite value (NaN/Inf) anywhere in the 540x20 window
-  big mask: max |finite value| > 1.5 (the data is otherwise [0,1]-normalized;
-            the corrupted files contain garbage up to 3.4e38, float32 max)
-
-Expected result on the pristine Kaggle download (RESULTS.md defect 5):
-  nan: 9,070 True | big: 9,072 True | union: 9,072 -- all windows in dataset
-  files 487-499 (the final 13 files), window indices 350,922-359,999.
-
-Usage:
-  PYTHONUTF8=1 .venv/Scripts/python.exe generate_corruption_masks.py \
-      [--data-dir <dir containing csi_windows.npy>] [--out-dir results]
-"""
-
-import argparse
-import os
-import sys
-
-import numpy as np
-
-HERE = os.path.dirname(os.path.abspath(__file__))
-RESULTS = os.path.join(HERE, "results")
-
-EXPECTED = {"nan": 9070, "big": 9072, "union": 9072,
-            "files": (487, 499), "windows": (350922, 359999)}
-
-
-def scan(csi_path, chunk=4000):
-    """Chunked scan of the (mmap'd) windows array; returns (nan_mask, big_mask)."""
-    csi = np.load(csi_path, mmap_mode="r")
-    n = len(csi)
-    nan_mask = np.zeros(n, dtype=bool)
-    big_mask = np.zeros(n, dtype=bool)
-    for i in range(0, n, chunk):
-        block = np.asarray(csi[i:i + chunk])
-        finite = np.isfinite(block)
-        nan_mask[i:i + chunk] = (~finite).any(axis=(1, 2))
-        big_mask[i:i + chunk] = (
-            np.abs(np.where(finite, block, 0)).max(axis=(1, 2)) > 1.5)
-        if (i // chunk) % 10 == 0:
-            print(f"  scanned {min(i + chunk, n):,}/{n:,} windows "
-                  f"(nan={int(nan_mask.sum()):,} big={int(big_mask.sum()):,})",
-                  flush=True)
-    return nan_mask, big_mask
-
-
-def describe_files(data_dir, mask):
-    """Map marked windows to dataset file indices via window_info.npz."""
-    info = os.path.join(data_dir, "window_info.npz")
-    if not os.path.exists(info):
-        return None
-    w2f = np.load(info)["window_to_file"]
-    return np.unique(w2f[mask])
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description="Regenerate the corruption masks from a PRISTINE "
-                    "(uncleaned) kagglehub download. See module docstring.")
-    parser.add_argument("--data-dir", default=os.path.join(
-        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
-        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"),
-        help="Directory containing csi_windows.npy (PRISTINE copy)")
-    parser.add_argument("--out-dir", default=RESULTS,
-                        help="Where to write the two .npy masks")
-    parser.add_argument("--chunk", type=int, default=4000,
-                        help="Windows per scan chunk (memory/speed tradeoff)")
-    args = parser.parse_args()
-
-    csi_path = os.path.join(args.data_dir, "csi_windows.npy")
-    if not os.path.exists(csi_path):
-        sys.exit(f"csi_windows.npy not found in {args.data_dir}")
-
-    print(f"scanning {csi_path} (chunk={args.chunk}) ...")
-    nan_mask, big_mask = scan(csi_path, args.chunk)
-    union = nan_mask | big_mask
-    print(f"nan: {int(nan_mask.sum()):,} | big: {int(big_mask.sum()):,} | "
-          f"union: {int(union.sum()):,} of {len(union):,} windows")
-
-    # ---- sanity check: an all-False result means a CLEANED copy ------------
-    if not union.any():
-        sys.exit(
-            "ERROR: scan found ZERO corrupted windows.\n"
-            "\n"
-            "The pristine Kaggle download (kaka2434/wiflow-dataset v1) is "
-            "known to contain\n"
-            "9,072 corrupted windows (NaN/Inf + amplitudes up to 3.4e38) in "
-            "dataset files\n"
-            "487-499 (RESULTS.md, reproducibility defect 5). Finding none "
-            "means this copy\n"
-            "has almost certainly already been repaired by remote/clean_v2.py "
-            "(or clean_nan.py),\n"
-            "which zeroes the corrupted windows IN PLACE -- after that the "
-            "corruption evidence\n"
-            "is gone and the masks CANNOT be regenerated from this copy.\n"
-            "\n"
-            "Refusing to overwrite the committed ground-truth masks with "
-            "all-False ones.\n"
-            "Re-download the dataset (kagglehub.dataset_download("
-            "'kaka2434/wiflow-dataset'))\n"
-            "and point --data-dir at the fresh, uncleaned copy.")
-
-    files = describe_files(args.data_dir, union)
-    if files is not None:
-        print(f"marked windows span dataset files {files.min()}-{files.max()}: "
-              f"{files.tolist()}")
-        lo, hi = EXPECTED["files"]
-        if files.min() != lo or files.max() != hi:
-            print(f"WARNING: expected marked files exactly {lo}-{hi} "
-                  f"(the pristine v1 download); got {files.min()}-{files.max()}. "
-                  f"Different dataset version, or a partially cleaned copy?")
-    for name, mask, exp in (("nan", nan_mask, EXPECTED["nan"]),
-                            ("big", big_mask, EXPECTED["big"])):
-        if int(mask.sum()) != exp:
-            print(f"WARNING: {name} mask has {int(mask.sum()):,} True windows; "
-                  f"the pristine v1 download yields {exp:,}.")
-
-    os.makedirs(args.out_dir, exist_ok=True)
-    for name, mask in (("nan_windows_mask.npy", nan_mask),
-                       ("big_windows_mask.npy", big_mask)):
-        out = os.path.join(args.out_dir, name)
-        np.save(out, mask)
-        print(f"wrote {out} ({int(mask.sum()):,} True)")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,220 +0,0 @@
-"""ADR-152 edge optimization: ONNX export + onnxruntime CPU benchmark for the
-retrained WiFlow-STD checkpoint.
-
- Exports fp32 to ONNX. The axial attention reshapes with python ints taken
-  from tensor.size() (view(N*W, C, H)), so a traced graph bakes the batch
-  size; we first try a dynamic-batch export and verify it actually works at
-  batch sizes 1/2/64 -- if not, we fall back to fixed-batch exports.
- Verifies output parity vs torch on the stored fixture
-  (results/parity_fixture.npz, batch 2, seed 42): max abs diff < 1e-4.
- Measures onnxruntime CPU latency at batch 1 and 64 (median of N runs).
- Supplementary: onnxruntime dynamic int8 quantization of the exported model
-  (weight size datapoint for the paper's "~2.2 MB int8" claim).
-
-Usage:
-  .venv/Scripts/python.exe onnx_bench.py
-
-Writes/merges into results/edge_optimization.json under key "onnx".
-"""
-
-import json
-import os
-import platform
-import statistics
-import time
-import traceback
-
-import numpy as np
-import torch
-
-from _bench_common import RESULTS, import_upstream, load_wiflow_model
-
-import_upstream()  # sys.path + models stub + >1GB np.load mmap patch
-
-CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
-OUT_JSON = os.path.join(RESULTS, "edge_optimization.json")
-
-
-def load_fp32_model():
-    return load_wiflow_model(CHECKPOINT)
-
-
-def try_export(model, path, batch, dynamic, opset=17):
-    """Returns (ok, exporter_used, error)."""
-    x = torch.rand(batch, 540, 20)
-    attempts = []
-    if dynamic:
-        attempts.append(("dynamo", dict(dynamo=True,
-                                        dynamic_shapes={"x": {0: "batch"}})))
-        attempts.append(("torchscript", dict(dynamo=False,
-                                             dynamic_axes={"input": {0: "batch"},
-                                                           "output": {0: "batch"}})))
-    else:
-        attempts.append(("torchscript", dict(dynamo=False)))
-        attempts.append(("dynamo", dict(dynamo=True)))
-    last_err = None
-    for name, kw in attempts:
-        try:
-            with torch.no_grad():
-                torch.onnx.export(model, (x,), path, opset_version=opset,
-                                  input_names=["input"], output_names=["output"],
-                                  **kw)
-            return True, name, None
-        except Exception as e:  # noqa: BLE001
-            last_err = f"{name}: {type(e).__name__}: {e}"
-            traceback.print_exc()
-    return False, None, last_err
-
-
-def ort_session(path):
-    import onnxruntime as ort
-    return ort.InferenceSession(path, providers=["CPUExecutionProvider"])
-
-
-def ort_run(sess, x):
-    inp = sess.get_inputs()[0].name
-    return sess.run(None, {inp: x})[0]
-
-
-def bench_ort(sess, batch, n_runs):
-    rng = np.random.default_rng(123)
-    x = rng.random((batch, 540, 20), dtype=np.float32)
-    for _ in range(max(5, n_runs // 10)):
-        ort_run(sess, x)
-    times = []
-    for _ in range(n_runs):
-        t0 = time.perf_counter()
-        ort_run(sess, x)
-        times.append(time.perf_counter() - t0)
-    med = statistics.median(times)
-    return {
-        "batch_size": batch,
-        "runs": n_runs,
-        "median_ms_per_batch": med * 1e3,
-        "median_ms_per_window": med * 1e3 / batch,
-        "windows_per_second": batch / med,
-    }
-
-
-def main():
-    import argparse
-    parser = argparse.ArgumentParser(
-        description="ONNX export + onnxruntime CPU benchmark for the "
-                    "retrained WiFlow-STD checkpoint (no options; see "
-                    "module docstring). NB: the published "
-                    "retrained_fp32_dynamic.onnx came from the TorchScript "
-                    "exporter; on newer torch the dynamo attempt may succeed "
-                    "first and produce a different (external-data) artifact.")
-    parser.parse_args()
-
-    import onnxruntime
-    model = load_fp32_model()
-    results = {
-        "env": {
-            "torch": torch.__version__,
-            "onnxruntime": onnxruntime.__version__,
-            "platform": platform.platform(),
-        },
-    }
-
-    fixture = np.load(os.path.join(RESULTS, "parity_fixture.npz"))
-    fx, fy = fixture["input"], fixture["output"]  # (2,540,20) -> (2,15,2)
-
-    # ---- export: dynamic batch first, fall back to fixed --------------------
-    dyn_path = os.path.join(RESULTS, "retrained_fp32_dynamic.onnx")
-    ok, exporter, err = try_export(model, dyn_path, batch=2, dynamic=True)
-    dynamic_works = False
-    if ok:
-        # verify the dynamic graph really runs at other batch sizes
-        try:
-            sess = ort_session(dyn_path)
-            for b in (1, 2, 64):
-                y = ort_run(sess, np.zeros((b, 540, 20), dtype=np.float32))
-                assert y.shape == (b, 15, 2), y.shape
-            dynamic_works = True
-        except Exception as e:  # noqa: BLE001
-            print(f"dynamic-batch model does not generalize: {e}")
-
-    sessions = {}
-    if dynamic_works:
-        results["export"] = {"mode": "dynamic-batch", "exporter": exporter,
-                             "file": os.path.basename(dyn_path),
-                             "size_mb": os.path.getsize(dyn_path) / 1e6}
-        sess = ort_session(dyn_path)
-        sessions = {1: sess, 2: sess, 64: sess}
-        print(f"dynamic-batch export OK via {exporter}")
-    else:
-        results["export"] = {"mode": "fixed-batch", "fallback_reason": err,
-                             "files": {}}
-        for b in (1, 2, 64):
-            p = os.path.join(RESULTS, f"retrained_fp32_b{b}.onnx")
-            ok, exporter, err = try_export(model, p, batch=b, dynamic=False)
-            if not ok:
-                results["export"]["files"][str(b)] = {"error": err}
-                print(f"EXPORT FAILED at batch {b}: {err}")
-                continue
-            results["export"]["files"][str(b)] = {
-                "exporter": exporter, "file": os.path.basename(p),
-                "size_mb": os.path.getsize(p) / 1e6}
-            sessions[b] = ort_session(p)
-            print(f"fixed-batch {b} export OK via {exporter}")
-
-    # ---- parity vs torch on the fixture -------------------------------------
-    if 2 in sessions:
-        y_ort = ort_run(sessions[2], fx)
-        with torch.no_grad():
-            y_torch = model(torch.from_numpy(fx)).numpy()
-        results["parity"] = {
-            "fixture": "results/parity_fixture.npz (batch 2, seed 42)",
-            "max_abs_diff_vs_stored_fixture": float(np.abs(y_ort - fy).max()),
-            "max_abs_diff_vs_torch_now": float(np.abs(y_ort - y_torch).max()),
-            "pass_lt_1e-4": bool(np.abs(y_ort - y_torch).max() < 1e-4),
-        }
-        print("parity:", json.dumps(results["parity"], indent=2))
-
-    # ---- latency -------------------------------------------------------------
-    results["latency"] = {}
-    if 1 in sessions:
-        results["latency"]["batch1"] = bench_ort(sessions[1], 1, 100)
-        print(f"ORT batch 1:  {results['latency']['batch1']['median_ms_per_window']:.2f} ms/window")
-    if 64 in sessions:
-        results["latency"]["batch64"] = bench_ort(sessions[64], 64, 30)
-        print(f"ORT batch 64: {results['latency']['batch64']['median_ms_per_window']:.3f} ms/window")
-
-    # ---- supplementary: ORT dynamic int8 (size datapoint for the 2.2MB claim)
-    src = (dyn_path if dynamic_works
-           else os.path.join(RESULTS, "retrained_fp32_b1.onnx"))
-    if os.path.exists(src):
-        try:
-            from onnxruntime.quantization import QuantType, quantize_dynamic
-            q_path = os.path.join(RESULTS, "retrained_int8_ort_dynamic.onnx")
-            quantize_dynamic(src, q_path, weight_type=QuantType.QInt8)
-            entry = {"file": os.path.basename(q_path),
-                     "size_mb": os.path.getsize(q_path) / 1e6}
-            try:
-                qs = ort_session(q_path)
-                yq = ort_run(qs, fx[:1] if not dynamic_works else fx)
-                ref = fy[:1] if not dynamic_works else fy
-                entry["runs"] = True
-                entry["max_abs_diff_vs_fp32_fixture"] = float(np.abs(yq - ref).max())
-            except Exception as e:  # noqa: BLE001
-                entry["runs"] = False
-                entry["run_error"] = f"{type(e).__name__}: {e}"
-            results["ort_int8_dynamic_supplementary"] = entry
-            print("ORT int8:", json.dumps(entry, indent=2))
-        except Exception as e:  # noqa: BLE001
-            results["ort_int8_dynamic_supplementary"] = {
-                "error": f"{type(e).__name__}: {e}"}
-
-    merged = {}
-    if os.path.exists(OUT_JSON):
-        with open(OUT_JSON) as f:
-            merged = json.load(f)
-    merged["onnx"] = results
-    with open(OUT_JSON, "w") as f:
-        json.dump(merged, f, indent=2)
-    print(f"wrote {OUT_JSON}")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,228 +0,0 @@
-"""ADR-152 "optimize beyond SOTA": edge-optimization benchmark for the
-retrained WiFlow-STD checkpoint (results/retrained_best_pose_model.pth,
-~96% PCK@20, fp32 params 2,225,042).
-
-Measures, for fp32 / fp16 / dynamic-int8 torch variants:
-  (a) serialized state_dict size on disk,
-  (b) CPU inference latency per window at batch 1 and batch 64
-      (median of repeated runs, this Windows box),
-  (c) accuracy (PCK@20/50 + MPJPE, upstream metrics) on a corruption-free
-      random subset of the seed-42 file-level 70/15/15 test split
-      (same split as eval_repro.py; corrupted windows 487-499 excluded via
-      results/nan_windows_mask.npy | results/big_windows_mask.npy).
-
-Also verifies the paper's "~2.2 MB int8" size claim: reports which layer
-types torch dynamic quantization actually converts (the model contains NO
-nn.Linear -- it is Conv1d/Conv2d/BatchNorm only) and the real on-disk size.
-
-Usage:
-  .venv/Scripts/python.exe quantize_bench.py \
-      --data-dir C:/Users/ruv/.cache/kagglehub/datasets/kaka2434/wiflow-dataset/versions/1/preprocessed_csi_data \
-      [--subset 10000] [--skip-accuracy]
-
-Writes/merges into results/edge_optimization.json under key "torch".
-"""
-
-import argparse
-import json
-import os
-import platform
-import statistics
-import time
-
-import numpy as np
-import torch
-import torch.nn as nn
-from torch.utils.data import DataLoader
-
-from _bench_common import HERE, RESULTS, evaluate, import_upstream, load_wiflow_model
-
-import_upstream()  # sys.path + models stub + >1GB np.load mmap patch
-
-from dataset import (  # noqa: E402
-    PreprocessedCSIKeypointsDataset,
-    create_preprocessed_train_val_test_loaders,
-)
-
-CHECKPOINT = os.path.join(RESULTS, "retrained_best_pose_model.pth")
-
-
-def load_fp32_model():
-    # legacy upstream key remap inside is a harmless no-op on this checkpoint
-    return load_wiflow_model(CHECKPOINT)
-
-
-def state_dict_size_bytes(model, path):
-    torch.save(model.state_dict(), path)
-    return os.path.getsize(path)
-
-
-def bench_latency(model, batch_size, n_runs, dtype=torch.float32):
-    gen = torch.Generator().manual_seed(123)
-    x = torch.rand(batch_size, 540, 20, generator=gen).to(dtype)
-    with torch.no_grad():
-        for _ in range(max(5, n_runs // 10)):  # warmup
-            model(x)
-        times = []
-        for _ in range(n_runs):
-            t0 = time.perf_counter()
-            model(x)
-            times.append(time.perf_counter() - t0)
-    med = statistics.median(times)
-    return {
-        "batch_size": batch_size,
-        "runs": n_runs,
-        "median_ms_per_batch": med * 1e3,
-        "median_ms_per_window": med * 1e3 / batch_size,
-        "windows_per_second": batch_size / med,
-    }
-
-
-def build_test_subset(data_dir, subset_size, batch_size=64):
-    """Seed-42 file-level 70/15/15 test split (exactly as eval_repro.py),
-    minus corrupted windows, then a seed-42 random subset."""
-    dataset = PreprocessedCSIKeypointsDataset(
-        data_dir=data_dir, keypoint_scale=1000.0, enable_temporal_clean=True)
-    _tr, _va, test_loader = create_preprocessed_train_val_test_loaders(
-        dataset=dataset, batch_size=batch_size, num_workers=0, random_seed=42)
-    test_indices = np.asarray(test_loader.dataset.indices)
-
-    corrupted = (np.load(os.path.join(RESULTS, "nan_windows_mask.npy"))
-                 | np.load(os.path.join(RESULTS, "big_windows_mask.npy")))
-    clean = test_indices[~corrupted[test_indices]]
-    print(f"test split: {len(test_indices)} windows, "
-          f"{len(test_indices) - len(clean)} corrupted excluded, "
-          f"{len(clean)} clean")
-
-    if subset_size and subset_size < len(clean):
-        rng = np.random.default_rng(42)
-        clean = np.sort(rng.choice(clean, size=subset_size, replace=False))
-    subset = torch.utils.data.Subset(dataset, clean.tolist())
-    loader = DataLoader(subset, batch_size=batch_size, shuffle=False,
-                        num_workers=0)
-    return loader, len(clean)
-
-
-def quantize_int8_dynamic(fp32_model):
-    """torch.ao.quantization.quantize_dynamic on Linear/Conv where supported.
-    Returns (model, report) where report documents what actually quantized."""
-    qmodel = torch.ao.quantization.quantize_dynamic(
-        fp32_model, {nn.Linear, nn.Conv1d, nn.Conv2d}, dtype=torch.qint8)
-
-    quantized, total_params, quant_params = [], 0, 0
-    for name, mod in qmodel.named_modules():
-        cls = type(mod).__module__ + "." + type(mod).__name__
-        if "quantized" in cls:
-            w = mod.weight() if callable(getattr(mod, "weight", None)) else None
-            numel = w.numel() if w is not None else 0
-            quant_params += numel
-            quantized.append({"module": name, "class": cls, "params": numel})
-    for p in fp32_model.parameters():
-        total_params += p.numel()
-
-    n_linear = sum(isinstance(m, nn.Linear) for m in fp32_model.modules())
-    n_conv1d = sum(isinstance(m, nn.Conv1d) for m in fp32_model.modules())
-    n_conv2d = sum(isinstance(m, nn.Conv2d) for m in fp32_model.modules())
-    report = {
-        "eligible_module_counts": {
-            "nn.Linear": n_linear, "nn.Conv1d": n_conv1d, "nn.Conv2d": n_conv2d},
-        "modules_actually_quantized": quantized,
-        "n_modules_quantized": len(quantized),
-        "params_total": total_params,
-        "params_quantized": quant_params,
-        "params_quantized_fraction": quant_params / total_params,
-    }
-    return qmodel, report
-
-
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--data-dir", default=os.path.join(
-        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
-        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
-    parser.add_argument("--subset", type=int, default=10000)
-    parser.add_argument("--runs-b1", type=int, default=100)
-    parser.add_argument("--runs-b64", type=int, default=30)
-    parser.add_argument("--skip-accuracy", action="store_true")
-    parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
-    args = parser.parse_args()
-
-    torch.manual_seed(42)
-    results = {
-        "env": {
-            "torch": torch.__version__,
-            "platform": platform.platform(),
-            "processor": platform.processor(),
-            "num_threads": torch.get_num_threads(),
-            "checkpoint": os.path.relpath(CHECKPOINT, HERE),
-        },
-        "variants": {},
-    }
-
-    # ---- build variants ---------------------------------------------------
-    fp32 = load_fp32_model()
-    n_params = sum(p.numel() for p in fp32.parameters())
-    results["env"]["params"] = n_params
-    print(f"fp32 model: {n_params:,} params")
-
-    fp16 = load_fp32_model().half()
-
-    int8, q_report = quantize_int8_dynamic(load_fp32_model())
-    results["int8_dynamic_quant_report"] = q_report
-    print(f"int8 dynamic: {q_report['n_modules_quantized']} modules quantized, "
-          f"{q_report['params_quantized_fraction']*100:.1f}% of params")
-
-    variants = {
-        "fp32": (fp32, torch.float32, "retrained_fp32_resaved.pth"),
-        "fp16": (fp16, torch.float16, "retrained_fp16.pth"),
-        "int8_dynamic": (int8, torch.float32, "retrained_int8_dynamic.pth"),
-    }
-
-    # ---- (a) size + (b) latency -------------------------------------------
-    for name, (model, dtype, fname) in variants.items():
-        path = os.path.join(RESULTS, fname)
-        size = state_dict_size_bytes(model, path)
-        print(f"\n=== {name}: {size/1e6:.3f} MB on disk ({fname}) ===")
-        lat1 = bench_latency(model, 1, args.runs_b1, dtype)
-        lat64 = bench_latency(model, 64, args.runs_b64, dtype)
-        print(f"  batch 1:  {lat1['median_ms_per_window']:.2f} ms/window "
-              f"({lat1['windows_per_second']:.0f}/s)")
-        print(f"  batch 64: {lat64['median_ms_per_window']:.3f} ms/window "
-              f"({lat64['windows_per_second']:.0f}/s)")
-        results["variants"][name] = {
-            "file": fname,
-            "size_bytes": size,
-            "size_mb": size / 1e6,
-            "latency_batch1": lat1,
-            "latency_batch64": lat64,
-        }
-
-    # ---- (c) accuracy ------------------------------------------------------
-    if not args.skip_accuracy:
-        loader, n_clean = build_test_subset(args.data_dir, args.subset)
-        results["accuracy_subset"] = {
-            "description": "seed-42 file-level 70/15/15 test split, corrupted "
-                           "windows (files 487-499) excluded, seed-42 random "
-                           "subset",
-            "subset_size": min(args.subset, n_clean) if args.subset else n_clean,
-            "clean_test_total": n_clean,
-        }
-        for name, (model, dtype, _f) in variants.items():
-            print(f"\n=== accuracy: {name} ===")
-            results["variants"][name]["accuracy"] = evaluate(
-                model, loader, dtype=dtype, label=name)
-            print(json.dumps(results["variants"][name]["accuracy"], indent=2))
-
-    # ---- merge into edge_optimization.json ---------------------------------
-    merged = {}
-    if os.path.exists(args.out):
-        with open(args.out) as f:
-            merged = json.load(f)
-    merged["torch"] = results
-    with open(args.out, "w") as f:
-        json.dump(merged, f, indent=2)
-    print(f"\nwrote {args.out}")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,14 +0,0 @@
-import numpy as np, os
-d = os.path.expanduser('~/wiflow-std-bench/preprocessed_csi_data')
-csi = np.load(os.path.join(d, 'csi_windows.npy'), mmap_mode='r+')
-zeroed = 0
-chunk = 4000
-for i in range(0, len(csi), chunk):
-    block = csi[i:i+chunk]
-    finite = np.isfinite(block)
-    bad = (~finite).any(axis=(1, 2)) | (np.abs(np.where(finite, block, 0)).max(axis=(1, 2)) > 1.5)
-    if bad.any():
-        block[bad] = 0.0
-        zeroed += int(bad.sum())
-csi.flush()
-print(f'zeroed {zeroed} corrupted windows entirely')
@@ -1,112 +0,0 @@
-"""Evaluate the retrained WiFlow-STD checkpoint (ADR-152 §2.2a fallback).
-
-Scores the model produced by run.py (train_output/best_pose_model.pth or similar)
-on the seed-42 test split: full test set AND NaN-free subset (excluding windows
-that were zero-filled by clean_nan.py — file indices 487-499).
-
-NOTE: deployed to ruvultra (~/wiflow-std-bench) as a standalone single file,
-so it deliberately inlines its helpers. The reference implementations (upstream
-import shim, >1GB np.load mmap patch, key-remap loader, canonical evaluate
-loop) live in benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
-"""
-import json, os, random, sys
-
-import numpy as np
-import torch
-from torch.utils.data import DataLoader, Subset
-
-# csi_windows.npy is ~13 GB; mmap large arrays instead of eagerly loading
-# ~15 GB into RAM (same patch as _bench_common._np_load_mmap).
-_np_load = np.load
-
-
-def _np_load_mmap(path, *a, **kw):
-    if (isinstance(path, str) and path.endswith('.npy')
-            and os.path.getsize(path) > 1 << 30 and 'mmap_mode' not in kw):
-        kw['mmap_mode'] = 'r'
-    return _np_load(path, *a, **kw)
-
-
-np.load = _np_load_mmap
-
-sys.path.insert(0, os.path.expanduser('~/wiflow-std-bench/upstream'))
-from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders
-from models.pose_model import WiFlowPoseModel
-from utils.metrics import calculate_pck, calculate_mpjpe
-
-
-def find_checkpoint():
-    cands = []
-    for root, _, files in os.walk(os.path.expanduser('~/wiflow-std-bench/train_output')):
-        for f in files:
-            if f.endswith('.pth'):
-                cands.append(os.path.join(root, f))
-    # also upstream/test default output dir
-    for root, _, files in os.walk(os.path.expanduser('~/wiflow-std-bench/upstream')):
-        for f in files:
-            if f.endswith('.pth') and 'best' in f and 'cross_dataset' not in root:
-                p = os.path.join(root, f)
-                if os.path.getmtime(p) > os.path.getmtime(os.path.expanduser('~/wiflow-std-bench/train.log')) - 86400 * 2:
-                    cands.append(p)
-    cands = [c for c in cands if not c.endswith('upstream/best_pose_model.pth')]
-    if not cands:
-        sys.exit('no retrained checkpoint found')
-    return max(cands, key=os.path.getmtime)
-
-
-def evaluate(model, loader, device):
-    model.eval()
-    totals = {t: 0.0 for t in (0.1, 0.2, 0.3, 0.4, 0.5)}
-    total_mpe, n = 0.0, 0
-    with torch.no_grad():
-        for bx, by in loader:
-            bx, by = bx.to(device), by.to(device)
-            out = model(bx)
-            bs = by.size(0)
-            total_mpe += calculate_mpjpe(out, by) * bs
-            pck = calculate_pck(out, by, thresholds=list(totals))
-            for t in totals:
-                totals[t] += pck[t] * bs
-            n += bs
-    return {'samples': n, 'mpjpe': total_mpe / n,
-            **{f'pck@{int(t*100)}': totals[t] / n for t in totals}}
-
-
-random.seed(42); np.random.seed(42); torch.manual_seed(42)
-torch.cuda.manual_seed_all(42)
-torch.backends.cudnn.deterministic = True
-
-d = os.path.expanduser('~/wiflow-std-bench/preprocessed_csi_data')
-dataset = PreprocessedCSIKeypointsDataset(data_dir=d, keypoint_scale=1000.0,
-                                          enable_temporal_clean=True)
-_, _, test_loader = create_preprocessed_train_val_test_loaders(
-    dataset=dataset, batch_size=256, num_workers=2, random_seed=42)
-
-device = torch.device('cuda')
-ckpt = find_checkpoint()
-print('checkpoint:', ckpt)
-model = WiFlowPoseModel(dropout=0.5).to(device)
-state = torch.load(ckpt, map_location=device, weights_only=True)
-renames = {'att.': 'attention.', 'final_conv.': 'decoder.'}
-state = {next((new + k[len(old):] for old, new in renames.items()
-               if k.startswith(old)), k): v for k, v in state.items()}
-model.load_state_dict(state, strict=True)
-
-results = {'checkpoint': ckpt}
-print('=== full test set ===')
-results['test_full'] = evaluate(model, test_loader, device)
-print(json.dumps(results['test_full'], indent=2))
-
-# NaN-free subset: exclude windows from corrupted files 487-499
-test_subset = test_loader.dataset            # Subset(dataset, test_indices)
-w2f = dataset.window_to_file
-clean_idx = [i for i in test_subset.indices if w2f[i] < 487]
-print(f'=== NaN-free test subset ({len(clean_idx)} of {len(test_subset.indices)}) ===')
-clean_loader = DataLoader(Subset(dataset, clean_idx), batch_size=256, shuffle=False)
-results['test_clean'] = evaluate(model, clean_loader, device)
-print(json.dumps(results['test_clean'], indent=2))
-
-out = os.path.expanduser('~/wiflow-std-bench/eval_retrained.json')
-with open(out, 'w') as f:
-    json.dump(results, f, indent=2)
-print('wrote', out)
@@ -1,374 +0,0 @@
-"""ADR-152 SS2.2 measurement (b): WiFlow-STD fine-tuned on our fresh ESP32 paired dataset.
-
-Dataset: ~/wiflow-std-bench/paired-20260610.jsonl -- 2,046 paired windows collected
-2026-06-10 22:10-22:40 (ONE subject, ONE room, ONE ESP32 node, varied poses).
-Per record: csi = flat float32 list, csi_shape, kp = 17 COCO [x, y] normalized [0,1]
-camera coords, conf (MediaPipe mean confidence, all > 0.5 in this set), ts_start/ts_end.
-Aligner: scripts/align-ground-truth.js, non-overlapping 20-frame windows (~0.42 s each).
-
-Dataset findings (MEASURED on this file, 2026-06-10):
-  - csi_shape is HETEROGENEOUS, not uniformly [70, 20]: 1,347x [70,20], 284x [134,20],
-    243x [26,20], 130x [12,20], 42x [20,20]. The ESP32 stream emits mixed frame types
-    and the aligner stamps each window's subcarrier count from frame[0]
-    (extractCsiMatrix: nSc = window[0].subcarriers), zero-padding/truncating the rest.
-    Even native-70 windows contain ~20.4% internally zero-padded short frames
-    (subcarriers 40..69 all-zero for those frames).
-  - LAYOUT BUG: the aligner fills matrix[f * nSc + s] (frame-major) but declares
-    shape [nSc, nFrames]. The true layout is (frame, subcarrier); we reshape
-    (nFrames, nSc) and transpose. Confirmed by coherent per-frame zero-tails.
-  - Handling here (primary suite, "all2046"): every frame's subcarrier axis is
-    linearly resampled to 70 bins (np.interp over a normalized index domain;
-    identity for native-70 frames) so the pre-registered n=2,046 and split sizes
-    hold. Secondary suite ("native70") restricts to the 1,347 native [70,20]
-    windows (temporal 70/15/15 of those) as a homogeneity robustness check.
-
-Pre-registered protocol (followed exactly):
-  1. TEMPORAL split (records are time-sorted; asserted): first 70% train (1,432),
-     next 15% val (307), last 15% test (307). No shuffling across time. Seed 42
-     for everything else.
-  2. Model: upstream WiFlow-STD trunk (WiFlowPoseModel) with a learned 1x1 Conv1d
-     projection 70->540 prepended, and K=17 via the parameter-free adaptive pool
-     (AdaptiveAvgPool2d((17, 1)) instead of (15, 1)) -- pretrained weights load
-     for any K. CSI normalization: divide by the TRAIN-split 99th-percentile
-     amplitude, clip to [0, 1] (documented in output JSON).
-  3. Three runs, <=60 epochs, early-stop patience 8 on val MPJPE, batch 32,
-     AdamW, fp32 (no autocast):
-       (i)   pretrained-init: trunk init from upstream/test/best_pose_model.pth
-             (the measurement-(a) retrained checkpoint, ~96% PCK@20 on WiFlow data;
-             key remap att.->attention. / final_conv.->decoder. applied defensively
-             as in eval_repro.py -- a no-op for this checkpoint, which already uses
-             the new names). Discriminative lr: adapter 1e-4, trunk 1e-5.
-       (ii)  scratch: same architecture, random init, all params lr 1e-4.
-       (iii) frozen-trunk: pretrained trunk frozen (requires_grad=False AND held in
-             .eval() so BatchNorm running stats cannot drift -- pure transfer probe);
-             only the 70->540 adapter trains, lr 1e-4.
-  4. Metrics on the temporal TEST split: torso-normalized PCK@10/20/30/40/50 and
-     MPJPE. Upstream utils/metrics.py calculate_pck(use_torso_norm=True) hardcodes
-     NECK_IDX/PELVIS_IDX = 2, 12 -- a 15-keypoint convention that is WRONG for our
-     17 COCO keypoints (2 = right_eye, 12 = right_hip). We therefore reimplement the
-     identical math (per-frame norm distance, clamp min 0.01, mean over all
-     keypoints x frames) with torso = ||l_shoulder(5) - l_hip(11)||.
-     Also reported: prediction std across test frames (constant-pose detector;
-     must be > 0) and the mean-pose-predictor baseline (train-split mean pose
-     evaluated on test -- the honesty bar).
-
-Usage (on ruvultra):
-  nice -n 10 nohup ~/wiflow-std-bench/venv/bin/python train_measb.py > train_measb.log 2>&1 &
-
-NOTE: deployed to ruvultra as a standalone single file, so it deliberately
-inlines its helpers. The reference implementations (upstream import shim,
-np.load mmap patch, key-remap loader, canonical evaluate loop) live in
-benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
-"""
-
-import json
-import os
-import random
-import sys
-import time
-
-import numpy as np
-import torch
-import torch.nn as nn
-
-BENCH = os.path.expanduser("~/wiflow-std-bench")
-UPSTREAM = os.path.join(BENCH, "upstream")
-MEASB = os.path.join(BENCH, "measb")
-DATA = os.path.join(BENCH, "paired-20260610.jsonl")
-CHECKPOINT = os.path.join(UPSTREAM, "test", "best_pose_model.pth")
-
-sys.path.insert(0, UPSTREAM)
-
-# Upstream defect (1): models/__init__.py imports a name tcn.py does not define.
-# Register a stub package so the broken __init__ never executes (as eval_repro.py).
-import types  # noqa: E402
-
-_models_pkg = types.ModuleType("models")
-_models_pkg.__path__ = [os.path.join(UPSTREAM, "models")]
-sys.modules["models"] = _models_pkg
-
-from models.pose_model import WiFlowPoseModel  # noqa: E402
-
-SEED = 42
-K = 17
-N_SUBC = 70
-TRUNK_IN = 540
-BATCH = 32          # <= 64 per protocol (GPU shared with the efficiency sweep)
-MAX_EPOCHS = 60
-PATIENCE = 8
-LR_ADAPTER = 1e-4
-LR_TRUNK_FT = 1e-5  # 10x lower for the pretrained trunk vs the fresh adapter
-L_SHOULDER, L_HIP = 5, 11
-THRESHOLDS = (0.1, 0.2, 0.3, 0.4, 0.5)
-
-
-def set_seed(seed=SEED):
-    random.seed(seed)
-    np.random.seed(seed)
-    torch.manual_seed(seed)
-    if torch.cuda.is_available():
-        torch.cuda.manual_seed_all(seed)
-    torch.backends.cudnn.deterministic = True
-    torch.backends.cudnn.benchmark = False
-
-
-def resample_subcarriers(frame_major, n_out=N_SUBC):
-    """(nFrames, nSc) -> (nFrames, n_out) by per-frame linear interpolation.
-
-    Identity for nSc == n_out. Normalized index domain [0, 1] on both sides.
-    """
-    nf, nsc = frame_major.shape
-    if nsc == n_out:
-        return frame_major
-    xi = np.linspace(0.0, 1.0, nsc)
-    xo = np.linspace(0.0, 1.0, n_out)
-    return np.stack([np.interp(xo, xi, frame_major[f]) for f in range(nf)]).astype(np.float32)
-
-
-def load_dataset():
-    csi, kps, confs, ts, native70 = [], [], [], [], []
-    shape_counts = {}
-    with open(DATA) as f:
-        for line in f:
-            r = json.loads(line)
-            nsc, nf = r["csi_shape"]
-            shape_counts[f"{nsc}x{nf}"] = shape_counts.get(f"{nsc}x{nf}", 0) + 1
-            assert nf == 20, r["csi_shape"]
-            # Aligner layout bug: data is frame-major despite the declared
-            # [nSc, nFrames] shape -- reshape (nFrames, nSc), then resample the
-            # subcarrier axis to 70 and transpose to (70 subcarriers, 20 frames).
-            fm = np.asarray(r["csi"], dtype=np.float32).reshape(nf, nsc)
-            csi.append(resample_subcarriers(fm).T)
-            kp = np.asarray(r["kp"], dtype=np.float32)
-            assert kp.shape == (K, 2), kp.shape
-            kps.append(kp)
-            confs.append(r["conf"])
-            ts.append(r["ts_start"])
-            native70.append(nsc == N_SUBC)
-    assert all(ts[i] <= ts[i + 1] for i in range(len(ts) - 1)), "records not time-sorted"
-    return (np.stack(csi), np.stack(kps), np.asarray(confs, dtype=np.float32),
-            np.asarray(native70), shape_counts, ts[0], ts[-1])
-
-
-def temporal_split(n):
-    n_train = int(round(n * 0.70))
-    n_val = int(round(n * 0.15))
-    return slice(0, n_train), slice(n_train, n_train + n_val), slice(n_train + n_val, n)
-
-
-class AdaptedWiFlow(nn.Module):
-    """1x1 Conv1d adapter 70->540 + upstream WiFlow-STD trunk with K=17 pool head."""
-
-    def __init__(self, k=K, dropout=0.5):
-        super().__init__()
-        self.adapter = nn.Conv1d(N_SUBC, TRUNK_IN, kernel_size=1)
-        nn.init.kaiming_normal_(self.adapter.weight, mode="fan_out", nonlinearity="relu")
-        nn.init.constant_(self.adapter.bias, 0)
-        self.trunk = WiFlowPoseModel(dropout=dropout)
-        # K=17 via the parameter-free adaptive pool: decoder emits [B, 2, 15, 20]
-        # spatial maps; pooling H->17 instead of 15 yields [B, 17, 2] with no new
-        # parameters, so the pretrained state_dict loads strict=True for any K.
-        self.trunk.avg_pool = nn.AdaptiveAvgPool2d((k, 1))
-
-    def forward(self, x):
-        return self.trunk(self.adapter(x))
-
-
-def load_pretrained_trunk(trunk, path):
-    state = torch.load(path, map_location="cpu", weights_only=True)
-    # Defensive remap as in eval_repro.py (no-op for the retrained checkpoint).
-    renames = {"att.": "attention.", "final_conv.": "decoder."}
-    state = {next((new + k[len(old):] for old, new in renames.items()
-                   if k.startswith(old)), k): v
-             for k, v in state.items()}
-    trunk.load_state_dict(state, strict=True)
-
-
-def pck_torso(pred, target, thresholds=THRESHOLDS):
-    """Upstream calculate_pck math, torso = l_shoulder(5)<->l_hip(11) for 17-kp COCO."""
-    norm = torch.sqrt(((target[:, L_SHOULDER] - target[:, L_HIP]) ** 2).sum(dim=1))
-    norm = torch.clamp(norm, min=0.01)
-    dist = torch.sqrt(((pred - target) ** 2).sum(dim=2)) / norm.unsqueeze(1)
-    return {f"pck@{int(t * 100)}": (dist <= t).float().mean().item() for t in thresholds}
-
-
-def mpjpe(pred, target):
-    return torch.sqrt(((pred - target) ** 2).sum(dim=2)).mean().item()
-
-
-@torch.no_grad()
-def predict(model, x, batch=256):
-    model.eval()
-    return torch.cat([model(x[i:i + batch]) for i in range(0, len(x), batch)])
-
-
-def eval_preds(pred, target):
-    out = pck_torso(pred, target)
-    out["mpjpe"] = mpjpe(pred, target)
-    # Constant-pose detector: std across test frames per coordinate, mean over
-    # the 17x2 coordinates. 0.0 == degenerate constant predictor.
-    out["pred_std"] = pred.std(dim=0).mean().item()
-    return out
-
-
-def train_run(name, x_tr, y_tr, x_va, y_va, device, pretrained, freeze_trunk,
-              lr_trunk):
-    set_seed(SEED)
-    model = AdaptedWiFlow().to(device)
-    if pretrained:
-        load_pretrained_trunk(model.trunk, CHECKPOINT)
-    if freeze_trunk:
-        for p in model.trunk.parameters():
-            p.requires_grad = False
-        groups = [{"params": model.adapter.parameters(), "lr": LR_ADAPTER}]
-    else:
-        groups = [{"params": model.adapter.parameters(), "lr": LR_ADAPTER},
-                  {"params": model.trunk.parameters(), "lr": lr_trunk}]
-    opt = torch.optim.AdamW(groups)
-    loss_fn = nn.MSELoss()
-
-    n = len(x_tr)
-    best_val, best_state, best_epoch, bad = float("inf"), None, -1, 0
-    history = []
-    t0 = time.time()
-    for epoch in range(MAX_EPOCHS):
-        model.train()
-        if freeze_trunk:
-            model.trunk.eval()  # keep BatchNorm running stats fixed: pure transfer
-        perm = torch.randperm(n, device=device)
-        ep_loss = 0.0
-        for i in range(0, n, BATCH):
-            idx = perm[i:i + BATCH]
-            opt.zero_grad()
-            loss = loss_fn(model(x_tr[idx]), y_tr[idx])
-            loss.backward()
-            opt.step()
-            ep_loss += loss.item() * len(idx)
-        val_mpjpe = mpjpe(predict(model, x_va), y_va)
-        history.append({"epoch": epoch, "train_mse": ep_loss / n, "val_mpjpe": val_mpjpe})
-        marker = ""
-        if val_mpjpe < best_val:
-            best_val, best_epoch, bad = val_mpjpe, epoch, 0
-            best_state = {k: v.detach().cpu().clone() for k, v in model.state_dict().items()}
-            marker = " *"
-        else:
-            bad += 1
-        print(f"[{name}] epoch {epoch:02d} train_mse {ep_loss / n:.6f} "
-              f"val_mpjpe {val_mpjpe:.5f}{marker}", flush=True)
-        if bad >= PATIENCE:
-            print(f"[{name}] early stop at epoch {epoch} (best {best_epoch})", flush=True)
-            break
-    model.load_state_dict(best_state)
-    torch.save(best_state, os.path.join(MEASB, f"{name}_best.pth"))
-    return model, {"best_epoch": best_epoch, "best_val_mpjpe": best_val,
-                   "epochs_run": len(history), "wall_seconds": round(time.time() - t0, 1),
-                   "history": history}
-
-
-def run_suite(tag, csi, kps, device):
-    """Temporal 70/15/15 split, mean-pose baseline, three training runs."""
-    n = len(csi)
-    tr, va, te = temporal_split(n)
-    print(f"=== suite {tag}: n={n} train={tr.stop} val={va.stop - va.start} "
-          f"test={te.stop - te.start} ===", flush=True)
-
-    # CSI normalization constant from TRAIN split only.
-    train_p99 = float(np.percentile(csi[tr], 99))
-    train_max = float(csi[tr].max())
-    print(f"[{tag}] train p99={train_p99:.3f} max={train_max:.3f} -> /p99, clip [0,1]",
-          flush=True)
-    csi_n = np.clip(csi / train_p99, 0.0, 1.0).astype(np.float32)
-
-    x = torch.from_numpy(csi_n).to(device)
-    y = torch.from_numpy(kps).to(device)
-    x_tr, y_tr = x[tr], y[tr]
-    x_va, y_va = x[va], y[va]
-    x_te, y_te = x[te], y[te]
-
-    suite = {
-        "n_windows": n,
-        "split": {"n_train": int(tr.stop), "n_val": int(va.stop - va.start),
-                  "n_test": int(te.stop - te.start)},
-        "csi_norm": {"method": "divide by train-split p99 amplitude, clip [0,1]",
-                     "train_p99": train_p99, "train_max": train_max},
-        "runs": {},
-    }
-
-    # Honesty bar: mean-pose predictor fit on TRAIN, evaluated on TEST.
-    mean_pose = y_tr.mean(dim=0, keepdim=True).expand(len(y_te), -1, -1)
-    suite["mean_pose_baseline"] = eval_preds(mean_pose, y_te)
-    suite["mean_pose_baseline"]["note"] = "train-split mean pose; pred_std 0 by construction"
-    print(f"[{tag}] mean-pose baseline:", json.dumps(suite["mean_pose_baseline"]),
-          flush=True)
-
-    configs = [
-        ("pretrained", dict(pretrained=True, freeze_trunk=False, lr_trunk=LR_TRUNK_FT)),
-        ("scratch", dict(pretrained=False, freeze_trunk=False, lr_trunk=LR_ADAPTER)),
-        ("frozen_trunk", dict(pretrained=True, freeze_trunk=True, lr_trunk=0.0)),
-    ]
-    for name, cfg in configs:
-        print(f"=== run: {tag}/{name} {cfg} ===", flush=True)
-        model, train_info = train_run(f"{tag}_{name}", x_tr, y_tr, x_va, y_va,
-                                      device, **cfg)
-        test_metrics = eval_preds(predict(model, x_te), y_te)
-        n_trainable = sum(p.numel() for p in model.parameters() if p.requires_grad)
-        suite["runs"][name] = {"config": cfg, "trainable_params": n_trainable,
-                               "train": {k: v for k, v in train_info.items()
-                                         if k != "history"},
-                               "history": train_info["history"],
-                               "test": test_metrics}
-        print(f"[{tag}/{name}] TEST:", json.dumps(test_metrics), flush=True)
-    return suite
-
-
-def main():
-    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-    print(f"device {device}, torch {torch.__version__}", flush=True)
-    set_seed(SEED)
-
-    csi, kps, confs, native70, shape_counts, ts_first, ts_last = load_dataset()
-    print(f"shape distribution: {shape_counts}", flush=True)
-
-    results = {
-        "protocol": {
-            "dataset": DATA, "n_windows": len(csi),
-            "ts_first": ts_first, "ts_last": ts_last,
-            "conf_mean": float(confs.mean()), "conf_min": float(confs.min()),
-            "csi_shape_distribution": shape_counts,
-            "csi_layout_note": "aligner stores frame-major data under a transposed "
-                               "[nSc, nFrames] shape label; corrected on load",
-            "csi_resample": "per-frame linear interp of subcarrier axis to 70 bins "
-                            "(identity for native-70 frames); native-70 windows still "
-                            "contain ~20.4% internally zero-padded short frames",
-            "split": "temporal 70/15/15 (no shuffle across time)",
-            "model": "1x1 Conv1d 70->540 adapter + WiFlowPoseModel trunk, "
-                     "AdaptiveAvgPool2d((17,1)) head (parameter-free K=17)",
-            "checkpoint": CHECKPOINT,
-            "checkpoint_note": "measurement-(a) retrained checkpoint (~96% PCK@20 on "
-                               "WiFlow data); att./final_conv. remap applied "
-                               "defensively (no-op, already new-style keys)",
-            "optimizer": f"AdamW, adapter lr {LR_ADAPTER}, fine-tuned trunk lr "
-                         f"{LR_TRUNK_FT} (10x lower), scratch all {LR_ADAPTER}",
-            "batch": BATCH, "max_epochs": MAX_EPOCHS, "patience": PATIENCE,
-            "precision": "fp32", "seed": SEED,
-            "pck": "torso-normalized, torso = ||l_shoulder(5) - l_hip(11)||, "
-                   "clamp min 0.01, mean over keypoints x frames "
-                   "(upstream math; upstream 2/12 indices are a 15-kp convention)",
-        },
-        # Primary: all 2,046 windows (pre-registered n), subcarrier axis resampled.
-        "all2046": None,
-        # Secondary robustness check: the 1,347 native [70,20] windows only.
-        "native70": None,
-    }
-
-    results["all2046"] = run_suite("all2046", csi, kps, device)
-    results["native70"] = run_suite("native70", csi[native70], kps[native70], device)
-
-    out = os.path.join(MEASB, "measurement_b.json")
-    with open(out, "w") as f:
-        json.dump(results, f, indent=2)
-    print(f"wrote {out}", flush=True)
-
-
-if __name__ == "__main__":
-    main()
@@ -1,33 +0,0 @@
-#!/bin/bash
-set -ex
-cd ~/wiflow-std-bench
-
-# 1. clone upstream at the pinned commit
-if [ ! -d upstream ]; then
-  git clone https://github.com/DY2434/WiFlow-WiFi-Pose-Estimation-with-Spatio-Temporal-Decoupling upstream
-fi
-cd upstream && git checkout 06899d294a0f44709d601a53e91dbf24759daefb && cd ..
-
-# 2. documented deviation: fix upstream import bug (TemporalConvNet does not exist)
-sed -i 's/from .tcn import TemporalConvNet/from .tcn import TemporalBlock/; s/'"'"'TemporalConvNet'"'"'/'"'"'TemporalBlock'"'"'/' upstream/models/__init__.py
-
-# 3. venv: torch cu128 (RTX 5080 = sm_120 needs >=2.7; their pin 2.3.1 predates Blackwell)
-if [ ! -d venv ]; then
-  python3 -m venv venv
-  ./venv/bin/pip install -q --upgrade pip
-  ./venv/bin/pip install -q torch --index-url https://download.pytorch.org/whl/cu128
-  ./venv/bin/pip install -q numpy pandas matplotlib seaborn scikit-learn opencv-python-headless scipy tqdm psutil kagglehub
-fi
-./venv/bin/python -c "import torch; print(torch.__version__, torch.cuda.is_available(), torch.cuda.get_device_name(0))"
-
-# 4. dataset via kagglehub (anonymous, public dataset)
-DS=$(./venv/bin/python -c "import kagglehub; print(kagglehub.dataset_download('kaka2434/wiflow-dataset'))")
-echo "dataset at: $DS"
-
-# 5. run.py hardcodes ../preprocessed_csi_data relative to upstream/
-ln -sfn "$DS/preprocessed_csi_data" ~/wiflow-std-bench/preprocessed_csi_data
-
-# 6. train with upstream defaults (seed 42 set inside run.py)
-../venv/bin/python ../clean_nan.py 2>/dev/null || venv/bin/python clean_nan.py
-cd upstream
-../venv/bin/python run.py --gpu 0 --batch_size 64 --epochs 50 --output_dir ../train_output
@@ -1,332 +0,0 @@
-"""Configurable compact variants of the WiFlow-STD pose model (ADR-152 efficiency sweep).
-
-This is a parameterized copy of upstream models/{pose_model,tcn,convnet,attention}.py
-(DY2434/WiFlow @ 06899d29, Apache-2.0). upstream/ is NOT modified. Deviations from
-upstream, all forced by shrinking channels and documented per variant in run_sweep.py:
-
-1. TCN grouped-conv groups: upstream hardcodes groups=20, which does not divide
-   the compact channel counts (e.g. 270, 135, 85). Rule here:
-   - groups_mode='gcd20': per-conv groups = gcd(channels, 20)  (== 20 wherever
-     upstream's choice is valid, incl. the 540-ch input conv; falls back to the
-     largest common divisor with 20 otherwise).
-   - groups_mode='depthwise': groups = channels (tiny variant only).
-2. Conv2d downsampling strides: upstream uses 4 stride-(1,2) blocks because
-   240/2^4 = 15 == n_keypoints. With smaller TCN output widths that would leave
-   <15 rows and AdaptiveAvgPool2d((15,1)) would duplicate rows across keypoints.
-   Rule: halve the width only while the result stays >= 15 (stride-2 blocks
-   first, stride-1 after). Full model: 240 -> 4 halvings = upstream exactly.
-3. input_pw_groups (tiny only): the dense 540->c pointwise + residual downsample
-   in TCN block 1 cost 2*540*c params (a ~117k floor that alone exceeds the
-   tiny <100k budget). tiny groups these two convs (groups=4; 4 | gcd(540, 68)).
-4. Decoder mid-channels: upstream 64->32; here c_last -> max(c_last // 2, 4).
-"""
-import math
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-def tcn_groups(channels: int, mode: str) -> int:
-    if mode == 'depthwise':
-        return channels
-    if mode == 'gcd20':
-        return math.gcd(channels, 20)
-    raise ValueError(mode)
-
-
-# ---------------------------------------------------------------- TCN (copy of tcn.py)
-class Chomp1d(nn.Module):
-    def __init__(self, chomp_size):
-        super().__init__()
-        self.chomp_size = chomp_size
-
-    def forward(self, x):
-        return x[:, :, :-self.chomp_size].contiguous()
-
-
-class CompactGroupedTemporalBlock(nn.Module):
-    """Upstream InnerGroupedTemporalBlock with parameterized groups."""
-
-    def __init__(self, n_inputs, n_outputs, kernel_size, stride, dilation, padding,
-                 dropout=0.2, groups_mode='gcd20', pw_groups=1):
-        super().__init__()
-        g_in = tcn_groups(n_inputs, groups_mode)
-        g_out = tcn_groups(n_outputs, groups_mode)
-        self.groups = (g_in, g_out)
-        self.pw_groups = pw_groups
-
-        self.conv1_group = nn.Conv1d(n_inputs, n_inputs, kernel_size, stride=stride,
-                                     padding=padding, dilation=dilation,
-                                     groups=g_in, bias=False)
-        self.chomp1 = Chomp1d(padding) if padding > 0 else nn.Identity()
-        self.bn1_group = nn.BatchNorm1d(n_inputs)
-        self.relu1_group = nn.SiLU(inplace=True)
-
-        self.conv1_pw = nn.Conv1d(n_inputs, n_outputs, 1, groups=pw_groups, bias=False)
-        self.bn1_pw = nn.BatchNorm1d(n_outputs)
-        self.relu1_pw = nn.SiLU(inplace=True)
-        self.dropout1 = nn.Dropout(dropout)
-
-        self.conv2_group = nn.Conv1d(n_outputs, n_outputs, kernel_size, stride=1,
-                                     padding=padding, dilation=dilation,
-                                     groups=g_out, bias=False)
-        self.chomp2 = Chomp1d(padding) if padding > 0 else nn.Identity()
-        self.bn2_group = nn.BatchNorm1d(n_outputs)
-        self.relu2_group = nn.SiLU(inplace=True)
-
-        self.conv2_pw = nn.Conv1d(n_outputs, n_outputs, 1, bias=False)
-        self.bn2_pw = nn.BatchNorm1d(n_outputs)
-        self.relu2_pw = nn.SiLU(inplace=True)
-        self.dropout2 = nn.Dropout(dropout)
-
-        self.downsample = nn.Sequential(
-            nn.Conv1d(n_inputs, n_outputs, 1, groups=pw_groups, bias=False),
-            nn.BatchNorm1d(n_outputs)
-        ) if n_inputs != n_outputs else nn.Identity()
-
-    def forward(self, x):
-        res = self.downsample(x)
-        out = self.conv1_group(x)
-        out = self.chomp1(out)
-        out = self.bn1_group(out)
-        out = self.relu1_group(out)
-        out = self.conv1_pw(out)
-        out = self.bn1_pw(out)
-        out = self.relu1_pw(out)
-        out = self.dropout1(out)
-        out = self.conv2_group(out)
-        out = self.chomp2(out)
-        out = self.bn2_group(out)
-        out = self.relu2_group(out)
-        out = self.conv2_pw(out)
-        out = self.bn2_pw(out)
-        out = self.relu2_pw(out)
-        out = self.dropout2(out)
-        return F.silu(out + res)
-
-
-class CompactTemporalBlock(nn.Module):
-    def __init__(self, num_inputs, num_channels, kernel_size=3, dropout=0.2,
-                 groups_mode='gcd20', input_pw_groups=1):
-        super().__init__()
-        layers = []
-        for i, out_channels in enumerate(num_channels):
-            dilation_size = 2 ** i
-            in_channels = num_inputs if i == 0 else num_channels[i - 1]
-            layers.append(CompactGroupedTemporalBlock(
-                in_channels, out_channels, kernel_size, stride=1,
-                dilation=dilation_size, padding=(kernel_size - 1) * dilation_size,
-                dropout=dropout, groups_mode=groups_mode,
-                pw_groups=input_pw_groups if i == 0 else 1))
-        self.network = nn.Sequential(*layers)
-
-    def forward(self, x):
-        return self.network(x)
-
-
-# ------------------------------------------------------- Conv2d path (copy of convnet.py)
-class AsymmetricConvBlock(nn.Module):
-    """Upstream block with parameterized width stride (upstream: always (1,2))."""
-
-    def __init__(self, in_channels, out_channels, dropout=0.3, stride_w=2):
-        super().__init__()
-        self.block = nn.Sequential(
-            nn.Conv2d(in_channels, out_channels, kernel_size=(1, 3),
-                      stride=(1, stride_w), padding=(0, 1)),
-            nn.BatchNorm2d(out_channels),
-            nn.SiLU(inplace=True),
-            nn.Dropout2d(dropout),
-            nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
-            nn.BatchNorm2d(out_channels),
-            nn.SiLU(inplace=True),
-            nn.Dropout2d(dropout),
-            nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
-            nn.BatchNorm2d(out_channels)
-        )
-        self.downsample = nn.Sequential(
-            nn.Conv2d(in_channels, out_channels, kernel_size=1,
-                      stride=(1, stride_w), bias=False),
-            nn.BatchNorm2d(out_channels)
-        )
-        self.activation = nn.SiLU(inplace=True)
-
-    def forward(self, x):
-        return self.activation(self.block(x) + self.downsample(x))
-
-
-class ConvBlock1(nn.Module):
-    def __init__(self, in_channels, out_channels, dropout=0.3):
-        super().__init__()
-        self.block = nn.Sequential(
-            nn.Conv2d(in_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
-            nn.BatchNorm2d(out_channels),
-            nn.SiLU(inplace=True),
-            nn.Dropout2d(dropout),
-            nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
-            nn.BatchNorm2d(out_channels),
-            nn.SiLU(inplace=True),
-            nn.Dropout2d(dropout),
-            nn.Conv2d(out_channels, out_channels, kernel_size=(1, 3), padding=(0, 1)),
-            nn.BatchNorm2d(out_channels)
-        )
-        self.downsample = nn.Sequential(
-            nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, bias=False),
-            nn.BatchNorm2d(out_channels)
-        )
-        self.activation = nn.SiLU(inplace=True)
-
-    def forward(self, x):
-        return self.activation(self.block(x) + self.downsample(x))
-
-
-# ----------------------------------------------------- attention (verbatim attention.py)
-class AxialAttention(nn.Module):
-    def __init__(self, in_planes, out_planes, groups=8, stride=1, bias=False, width=False):
-        assert (in_planes % groups == 0) and (out_planes % groups == 0)
-        super().__init__()
-        self.in_planes = in_planes
-        self.out_planes = out_planes
-        self.groups = groups
-        self.group_planes = out_planes // groups
-        self.stride = stride
-        self.bias = bias
-        self.width = width
-        self.qkv_transform = nn.Conv1d(in_planes, out_planes * 3, kernel_size=1,
-                                       stride=1, padding=0, bias=False)
-        self.bn_qkv = nn.BatchNorm1d(out_planes * 3)
-        self.bn_similarity = nn.BatchNorm2d(groups)
-        self.bn_output = nn.BatchNorm1d(out_planes)
-        if stride > 1:
-            self.pooling = nn.AvgPool2d(stride, stride=stride)
-        nn.init.normal_(self.qkv_transform.weight.data, 0, math.sqrt(1. / self.in_planes))
-
-    def forward(self, x):
-        if self.width:
-            x = x.permute(0, 2, 1, 3)
-        else:
-            x = x.permute(0, 3, 1, 2)
-        N, W, C, H = x.shape
-        x = x.contiguous().view(N * W, C, H)
-        qkv = self.bn_qkv(self.qkv_transform(x))
-        qkv = qkv.reshape(N * W, 3, self.out_planes, H).permute(1, 0, 2, 3)
-        q, k, v = qkv[0], qkv[1], qkv[2]
-        q = q.reshape(N * W, self.groups, self.group_planes, H)
-        k = k.reshape(N * W, self.groups, self.group_planes, H)
-        v = v.reshape(N * W, self.groups, self.group_planes, H)
-        qk = torch.einsum('bgci, bgcj->bgij', q, k)
-        qk = self.bn_similarity(qk)
-        similarity = F.softmax(qk, dim=-1)
-        sv = torch.einsum('bgij,bgcj->bgci', similarity, v)
-        sv = sv.reshape(N * W, self.out_planes, H)
-        out = self.bn_output(sv)
-        out = out.view(N, W, self.out_planes, H)
-        if self.width:
-            out = out.permute(0, 2, 1, 3)
-        else:
-            out = out.permute(0, 2, 3, 1)
-        if self.stride > 1:
-            out = self.pooling(out)
-        return out
-
-
-class DualAxialAttention(nn.Module):
-    def __init__(self, in_planes, out_planes, groups=8, stride=1, bias=False):
-        super().__init__()
-        self.width_axis = AxialAttention(in_planes, out_planes, groups, stride, bias, width=True)
-        self.height_axis = AxialAttention(out_planes, out_planes, groups, stride, bias, width=False)
-
-    def forward(self, x):
-        return self.height_axis(self.width_axis(x))
-
-
-# --------------------------------------------------------------- full model
-def compute_strides(width: int, n_blocks: int, target: int = 15):
-    """Halve width while result stays >= target (upstream: 240 -> 4 halvings -> 15)."""
-    strides = []
-    for _ in range(n_blocks):
-        nxt = (width + 1) // 2  # conv k=3 s=2 p=1: out = ceil(in/2)
-        if nxt >= target:
-            strides.append(2)
-            width = nxt
-        else:
-            strides.append(1)
-    return strides, width
-
-
-class CompactWiFlowPoseModel(nn.Module):
-    """Parameterized upstream WiFlowPoseModel.
-
-    Upstream config == tcn_channels=[540,440,340,240], conv_channels=[8,16,32,64],
-    attn_groups=8, groups_mode='gcd20' (gcd(c,20)==20 for all upstream channels),
-    input_pw_groups=1 -> identical architecture, 2,225,042 params.
-    """
-
-    def __init__(self, tcn_channels, conv_channels, attn_groups,
-                 groups_mode='gcd20', input_pw_groups=1, dropout=0.3,
-                 num_subcarriers=540, num_keypoints=15):
-        super().__init__()
-        self.tcn = CompactTemporalBlock(
-            num_inputs=num_subcarriers, num_channels=tcn_channels, kernel_size=3,
-            dropout=dropout, groups_mode=groups_mode, input_pw_groups=input_pw_groups)
-
-        self.up = ConvBlock1(1, conv_channels[0])
-
-        strides, self.final_width = compute_strides(
-            tcn_channels[-1], len(conv_channels), target=num_keypoints)
-        self.conv_strides = strides
-        self.residual_blocks = nn.ModuleList()
-        in_channels = conv_channels[0]
-        for out_channels, s in zip(conv_channels, strides):
-            self.residual_blocks.append(
-                AsymmetricConvBlock(in_channels, out_channels, stride_w=s))
-            in_channels = out_channels
-
-        c_last = conv_channels[-1]
-        self.attention = DualAxialAttention(c_last, c_last, groups=attn_groups)
-
-        c_mid = max(c_last // 2, 4)
-        self.decoder = nn.Sequential(
-            nn.Conv2d(c_last, c_mid, kernel_size=3, padding=1),
-            nn.BatchNorm2d(c_mid),
-            nn.SiLU(inplace=True),
-            nn.Conv2d(c_mid, 2, kernel_size=1),
-            nn.BatchNorm2d(2),
-            nn.SiLU(inplace=True)
-        )
-        self.avg_pool = nn.AdaptiveAvgPool2d((num_keypoints, 1))
-        self._initialize_weights()
-
-    def _initialize_weights(self):
-        for m in self.modules():
-            if isinstance(m, nn.Conv1d):
-                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
-                if m.bias is not None:
-                    nn.init.constant_(m.bias, 0)
-            elif isinstance(m, (nn.BatchNorm1d, nn.LayerNorm)):
-                nn.init.constant_(m.weight, 1)
-                nn.init.constant_(m.bias, 0)
-            elif isinstance(m, nn.Linear):
-                nn.init.xavier_normal_(m.weight)
-                if m.bias is not None:
-                    nn.init.constant_(m.bias, 0)
-
-    def forward(self, x):
-        # [B, 540, 20]
-        x = self.tcn(x)                          # [B, C_tcn, 20]
-        x = x.transpose(1, 2).unsqueeze(1)       # [B, 1, 20, C_tcn]
-        x = self.up(x)
-        for block in self.residual_blocks:
-            x = block(x)                         # [B, C_conv, 20, W']
-        x = x.permute(0, 1, 3, 2)                # [B, C_conv, W', 20]
-        x = self.attention(x)
-        x = self.decoder(x)                      # [B, 2, W', 20]
-        x = self.avg_pool(x).squeeze(-1)         # [B, 2, 15]
-        return x.transpose(1, 2)                 # [B, 15, 2]
-
-
-def describe(model: 'CompactWiFlowPoseModel'):
-    params = sum(p.numel() for p in model.parameters())
-    tcn_g = [blk.groups for blk in model.tcn.network]
-    return {'params': params, 'tcn_groups_per_block': tcn_g,
-            'conv_strides': model.conv_strides, 'final_width': model.final_width}
@@ -1,278 +0,0 @@
-"""WiFlow-STD compact-variant efficiency sweep (ADR-152) — sequential overnight runner.
-
-Trains compact variants of the upstream WiFlow-STD architecture on the same
-data/split as the full-size reference retraining (seed 42, file-level 70/15/15,
-upstream dataset.py) and evaluates PCK@10..50 + MPJPE on the full test split and
-the corruption-free test subset (file indices < 487).
-
-Training mirrors upstream run.py/train.py defaults except:
- fp32 only (no fp16 autocast / GradScaler — avoids the BN-poisoning trap
-  documented in RESULTS.md defect 5; data on disk is already cleaned).
- batch 64 (kept modest: another GPU job may share the 16 GB card tonight).
- scheduler + early stopping keyed on val MPJPE (upstream early-stops on val MPE
-  with patience 5; same here).
-
-Usage:
-  venv/bin/python sweep/run_sweep.py --dry-run    # param counts only
-  nohup venv/bin/python sweep/run_sweep.py > sweep/sweep.log 2>&1 &
-
-Idempotent: variants already present in sweep/results.jsonl are skipped.
-
-NOTE: deployed to ruvultra (~/wiflow-std-bench/sweep) as a standalone file, so
-it deliberately inlines its helpers. The reference implementations (upstream
-import shim, >1GB np.load mmap patch, key-remap loader, canonical evaluate
-loop) live in benchmarks/wiflow-std/_bench_common.py — keep copies in sync.
-"""
-import argparse
-import copy
-import json
-import os
-import random
-import sys
-import time
-
-import numpy as np
-import torch
-from torch.utils.data import DataLoader, Subset
-
-# csi_windows.npy is ~13 GB; mmap large arrays instead of eagerly loading
-# ~15 GB into RAM (same patch as _bench_common._np_load_mmap).
-_np_load = np.load
-
-
-def _np_load_mmap(path, *a, **kw):
-    if (isinstance(path, str) and path.endswith('.npy')
-            and os.path.getsize(path) > 1 << 30 and 'mmap_mode' not in kw):
-        kw['mmap_mode'] = 'r'
-    return _np_load(path, *a, **kw)
-
-
-np.load = _np_load_mmap
-
-BENCH = os.path.expanduser('~/wiflow-std-bench')
-SWEEP = os.path.join(BENCH, 'sweep')
-sys.path.insert(0, os.path.join(BENCH, 'upstream'))
-sys.path.insert(0, SWEEP)
-
-from dataset import PreprocessedCSIKeypointsDataset, create_preprocessed_train_val_test_loaders  # noqa: E402
-from losses.pose_loss import PoseLoss          # noqa: E402
-from utils.metrics import calculate_pck, calculate_mpjpe  # noqa: E402
-from model_compact import CompactWiFlowPoseModel, describe  # noqa: E402
-
-VARIANTS = [
-    # name, tcn_channels, conv_channels, attn_groups, groups_mode, input_pw_groups
-    dict(name='half',    tcn=[270, 220, 170, 120], conv=[4, 8, 16, 32], attn_groups=4,
-         groups_mode='gcd20', input_pw_groups=1),
-    dict(name='quarter', tcn=[135, 110, 85, 60],   conv=[2, 4, 8, 16],  attn_groups=2,
-         groups_mode='gcd20', input_pw_groups=1),
-    dict(name='tiny',    tcn=[68, 56, 44, 32],     conv=[2, 4, 8, 16],  attn_groups=2,
-         groups_mode='depthwise', input_pw_groups=4),
-]
-
-BATCH = 64
-EPOCHS = 50
-PATIENCE = 5
-LR = 1e-4
-WEIGHT_DECAY = 5e-5
-SEED = 42
-CORRUPT_FILE_START = 487  # files 487-499 were zero-filled by clean_nan.py
-
-
-def set_seed(seed=SEED):
-    random.seed(seed)
-    np.random.seed(seed)
-    torch.manual_seed(seed)
-    torch.cuda.manual_seed_all(seed)
-    torch.backends.cudnn.deterministic = True
-    torch.backends.cudnn.benchmark = False
-
-
-def build_model(v, dropout=0.5):
-    return CompactWiFlowPoseModel(
-        tcn_channels=v['tcn'], conv_channels=v['conv'], attn_groups=v['attn_groups'],
-        groups_mode=v['groups_mode'], input_pw_groups=v['input_pw_groups'],
-        dropout=dropout)
-
-
-@torch.no_grad()
-def evaluate(model, loader, device):
-    model.eval()
-    totals = {t: 0.0 for t in (0.1, 0.2, 0.3, 0.4, 0.5)}
-    total_mpe, n = 0.0, 0
-    for bx, by in loader:
-        bx, by = bx.to(device), by.to(device)
-        out = model(bx)
-        bs = by.size(0)
-        total_mpe += calculate_mpjpe(out, by) * bs
-        pck = calculate_pck(out, by, thresholds=list(totals))
-        for t in totals:
-            totals[t] += pck[t] * bs
-        n += bs
-    return {'samples': n, 'mpjpe': total_mpe / n,
-            **{f'pck@{int(t * 100)}': totals[t] / n for t in totals}}
-
-
-def train_variant(v, dataset, device):
-    set_seed(SEED)
-    train_loader, val_loader, test_loader = create_preprocessed_train_val_test_loaders(
-        dataset=dataset, batch_size=BATCH, num_workers=2, random_seed=SEED)
-
-    set_seed(SEED)  # re-seed after split so init is split-independent
-    model = build_model(v).to(device)
-    info = describe(model)
-    print(f"[{v['name']}] params={info['params']:,} tcn_groups={info['tcn_groups_per_block']} "
-          f"conv_strides={info['conv_strides']} final_width={info['final_width']}", flush=True)
-
-    criterion = PoseLoss(position_weight=1.0, bone_weight=0.2, loss_type='smooth_l1')
-    optimizer = torch.optim.AdamW(model.parameters(), lr=LR, weight_decay=WEIGHT_DECAY,
-                                  betas=(0.9, 0.999))
-    scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
-        optimizer, mode='min', factor=0.5, patience=3, min_lr=LR / 1000,
-        cooldown=1, threshold=1e-4)
-
-    best_val_mpe = float('inf')
-    best_val_pck20 = 0.0
-    best_epoch = 0
-    best_state = None
-    patience_counter = 0
-    t0 = time.time()
-    error = None
-    epochs_run = 0
-
-    for epoch in range(1, EPOCHS + 1):
-        model.train()
-        ep_loss, nb = 0.0, 0
-        te = time.time()
-        for i, (bx, by) in enumerate(train_loader):
-            bx = bx.to(device, non_blocking=True)
-            by = by.to(device, non_blocking=True)
-            optimizer.zero_grad(set_to_none=True)
-            out = model(bx)
-            loss, _parts = criterion(out, by)
-            if not torch.isfinite(loss):
-                error = f'non-finite loss at epoch {epoch} step {i}'
-                break
-            loss.backward()
-            optimizer.step()
-            ep_loss += loss.item()
-            nb += 1
-            if epoch == 1 and i % 500 == 0:
-                print(f"[{v['name']}] e1 step {i}/{len(train_loader)} loss={loss.item():.5f}",
-                      flush=True)
-        if error:
-            break
-        epochs_run = epoch
-
-        val = evaluate(model, val_loader, device)
-        scheduler.step(val['mpjpe'])
-        lr_now = optimizer.param_groups[0]['lr']
-        print(f"[{v['name']}] epoch {epoch}/{EPOCHS} train_loss={ep_loss / max(nb, 1):.5f} "
-              f"val_mpjpe={val['mpjpe']:.5f} val_pck20={val['pck@20'] * 100:.2f}% "
-              f"lr={lr_now:.2e} ({time.time() - te:.0f}s)", flush=True)
-
-        if val['mpjpe'] < best_val_mpe:
-            best_val_mpe = val['mpjpe']
-            best_val_pck20 = val['pck@20']
-            best_epoch = epoch
-            best_state = copy.deepcopy(model.state_dict())
-            patience_counter = 0
-        else:
-            patience_counter += 1
-            if patience_counter >= PATIENCE:
-                print(f"[{v['name']}] early stop at epoch {epoch} (best {best_epoch})", flush=True)
-                break
-
-    train_seconds = time.time() - t0
-    result = {
-        'variant': v['name'], 'params': info['params'],
-        'tcn_channels': v['tcn'], 'conv_channels': v['conv'],
-        'attn_groups': v['attn_groups'], 'groups_mode': v['groups_mode'],
-        'input_pw_groups': v['input_pw_groups'],
-        'tcn_groups_per_block': info['tcn_groups_per_block'],
-        'conv_strides': info['conv_strides'], 'final_width': info['final_width'],
-        'batch_size': BATCH, 'max_epochs': EPOCHS, 'patience': PATIENCE,
-        'lr': LR, 'weight_decay': WEIGHT_DECAY, 'seed': SEED, 'precision': 'fp32',
-        'epochs_run': epochs_run, 'best_epoch': best_epoch,
-        'best_val_mpjpe': best_val_mpe if best_state else None,
-        'best_val_pck20': best_val_pck20 if best_state else None,
-        'train_seconds': round(train_seconds, 1),
-        'torch': torch.__version__, 'error': error,
-        'finished_utc': time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime()),
-    }
-
-    if best_state is not None:
-        ckpt = os.path.join(SWEEP, f"{v['name']}_best.pth")
-        torch.save(best_state, ckpt)
-        result['checkpoint'] = ckpt
-        model.load_state_dict(best_state)
-
-        eval_loader = DataLoader(test_loader.dataset, batch_size=256, shuffle=False,
-                                 num_workers=2)
-        result['test_full'] = evaluate(model, eval_loader, device)
-
-        w2f = dataset.window_to_file
-        clean_idx = [i for i in test_loader.dataset.indices if w2f[i] < CORRUPT_FILE_START]
-        clean_loader = DataLoader(Subset(dataset, clean_idx), batch_size=256,
-                                  shuffle=False, num_workers=2)
-        result['test_clean'] = evaluate(model, clean_loader, device)
-        print(f"[{v['name']}] TEST clean: pck20={result['test_clean']['pck@20'] * 100:.2f}% "
-              f"mpjpe={result['test_clean']['mpjpe']:.5f} | full: "
-              f"pck20={result['test_full']['pck@20'] * 100:.2f}%", flush=True)
-    return result
-
-
-def main():
-    ap = argparse.ArgumentParser()
-    ap.add_argument('--dry-run', action='store_true', help='print param counts and exit')
-    args = ap.parse_args()
-
-    if args.dry_run:
-        for v in VARIANTS:
-            m = build_model(v)
-            info = describe(m)
-            x = torch.randn(2, 540, 20)
-            m.eval()
-            y = m(x)
-            print(f"{v['name']:8s} params={info['params']:>9,} "
-                  f"tcn={v['tcn']} conv={v['conv']} attn_g={v['attn_groups']} "
-                  f"mode={v['groups_mode']} pw_g={v['input_pw_groups']} "
-                  f"tcn_groups={info['tcn_groups_per_block']} strides={info['conv_strides']} "
-                  f"W'={info['final_width']} out={tuple(y.shape)}")
-        return
-
-    results_path = os.path.join(SWEEP, 'results.jsonl')
-    done = set()
-    if os.path.exists(results_path):
-        with open(results_path) as f:
-            for line in f:
-                try:
-                    done.add(json.loads(line)['variant'])
-                except Exception:
-                    pass
-
-    device = torch.device('cuda')
-    print(f"torch {torch.__version__} on {torch.cuda.get_device_name(0)}", flush=True)
-    data_dir = os.path.join(BENCH, 'preprocessed_csi_data')
-    dataset = PreprocessedCSIKeypointsDataset(data_dir=data_dir, keypoint_scale=1000.0,
-                                              enable_temporal_clean=True)
-
-    for v in VARIANTS:
-        if v['name'] in done:
-            print(f"[{v['name']}] already in results.jsonl — skipping", flush=True)
-            continue
-        print(f"\n===== variant: {v['name']} =====", flush=True)
-        try:
-            result = train_variant(v, dataset, device)
-        except Exception as e:  # record and move on to next variant
-            import traceback
-            traceback.print_exc()
-            result = {'variant': v['name'], 'error': repr(e),
-                      'finished_utc': time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime())}
-        with open(results_path, 'a') as f:
-            f.write(json.dumps(result) + '\n')
-            f.flush()
-    print('\nSWEEP COMPLETE', flush=True)
-
-
-if __name__ == '__main__':
-    main()
@@ -1,772 +0,0 @@
-{
-  "torch": {
-    "env": {
-      "torch": "2.12.0+cpu",
-      "platform": "Windows-11-10.0.26200-SP0",
-      "processor": "Intel64 Family 6 Model 197 Stepping 2, GenuineIntel",
-      "num_threads": 16,
-      "checkpoint": "results\\retrained_best_pose_model.pth",
-      "params": 2225042
-    },
-    "variants": {
-      "fp32": {
-        "file": "retrained_fp32_resaved.pth",
-        "size_bytes": 9068948,
-        "size_mb": 9.068948,
-        "latency_batch1": {
-          "batch_size": 1,
-          "runs": 100,
-          "median_ms_per_batch": 24.903650000851485,
-          "median_ms_per_window": 24.903650000851485,
-          "windows_per_second": 40.15475642991324
-        },
-        "latency_batch64": {
-          "batch_size": 64,
-          "runs": 30,
-          "median_ms_per_batch": 184.02919999789447,
-          "median_ms_per_window": 2.875456249967101,
-          "windows_per_second": 347.77089723115813
-        },
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.9668200004577636,
-          "pck@50": 0.9915333324432373,
-          "mpjpe": 0.00936222033649683,
-          "wall_seconds": 37.85407733917236
-        }
-      },
-      "fp16": {
-        "file": "retrained_fp16.pth",
-        "size_bytes": 4580332,
-        "size_mb": 4.580332,
-        "latency_batch1": {
-          "batch_size": 1,
-          "runs": 100,
-          "median_ms_per_batch": 23.936699999467237,
-          "median_ms_per_window": 23.936699999467237,
-          "windows_per_second": 41.776853117691964
-        },
-        "latency_batch64": {
-          "batch_size": 64,
-          "runs": 30,
-          "median_ms_per_batch": 102.32584999903338,
-          "median_ms_per_window": 1.5988414062348966,
-          "windows_per_second": 625.4529036465817
-        },
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.966773332977295,
-          "pck@50": 0.9915066654205322,
-          "mpjpe": 0.009460017587244511,
-          "wall_seconds": 21.632277250289917
-        }
-      },
-      "int8_dynamic": {
-        "file": "retrained_int8_dynamic.pth",
-        "size_bytes": 9068948,
-        "size_mb": 9.068948,
-        "latency_batch1": {
-          "batch_size": 1,
-          "runs": 100,
-          "median_ms_per_batch": 18.105350000041653,
-          "median_ms_per_window": 18.105350000041653,
-          "windows_per_second": 55.23229321707117
-        },
-        "latency_batch64": {
-          "batch_size": 64,
-          "runs": 30,
-          "median_ms_per_batch": 168.77549999844632,
-          "median_ms_per_window": 2.6371171874757238,
-          "windows_per_second": 379.20195763359703
-        },
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.9668200004577636,
-          "pck@50": 0.9915333324432373,
-          "mpjpe": 0.00936222033649683,
-          "wall_seconds": 45.35376596450806
-        }
-      }
-    },
-    "int8_dynamic_quant_report": {
-      "eligible_module_counts": {
-        "nn.Linear": 0,
-        "nn.Conv1d": 21,
-        "nn.Conv2d": 22
-      },
-      "modules_actually_quantized": [],
-      "n_modules_quantized": 0,
-      "params_total": 2225042,
-      "params_quantized": 0,
-      "params_quantized_fraction": 0.0
-    },
-    "accuracy_subset": {
-      "description": "seed-42 file-level 70/15/15 test split, corrupted windows (files 487-499) excluded, seed-42 random subset",
-      "subset_size": 10000,
-      "clean_test_total": 10000
-    }
-  },
-  "onnx": {
-    "env": {
-      "torch": "2.12.0+cpu",
-      "onnxruntime": "1.26.0",
-      "platform": "Windows-11-10.0.26200-SP0"
-    },
-    "export": {
-      "mode": "dynamic-batch",
-      "exporter": "torchscript",
-      "file": "retrained_fp32_dynamic.onnx",
-      "size_mb": 8.971781
-    },
-    "parity": {
-      "fixture": "results/parity_fixture.npz (batch 2, seed 42)",
-      "max_abs_diff_vs_stored_fixture": 2.384185791015625e-07,
-      "max_abs_diff_vs_torch_now": 2.384185791015625e-07,
-      "pass_lt_1e-4": true
-    },
-    "latency": {
-      "batch1": {
-        "batch_size": 1,
-        "runs": 100,
-        "median_ms_per_batch": 2.5410999987798277,
-        "median_ms_per_window": 2.5410999987798277,
-        "windows_per_second": 393.5303610563043
-      },
-      "batch64": {
-        "batch_size": 64,
-        "runs": 30,
-        "median_ms_per_batch": 181.95204999938142,
-        "median_ms_per_window": 2.8430007812403346,
-        "windows_per_second": 351.7410218803118
-      }
-    },
-    "ort_int8_dynamic_supplementary": {
-      "file": "retrained_int8_ort_dynamic.onnx",
-      "size_mb": 2.438794,
-      "runs": true,
-      "max_abs_diff_vs_fp32_fixture": 0.00827130675315857
-    }
-  },
-  "onnx_accuracy": {
-    "onnx_fp32": {
-      "samples": 10000,
-      "pck@20": 0.9668200004577636,
-      "pck@50": 0.9915333324432373,
-      "mpjpe": 0.00936222568154335,
-      "wall_seconds": 22.34790802001953
-    },
-    "onnx_int8_ort_dynamic": {
-      "samples": 10000,
-      "pck@20": 0.965240001964569,
-      "pck@50": 0.9915466655731201,
-      "mpjpe": 0.01108054072111845,
-      "wall_seconds": 55.742953062057495
-    }
-  },
-  "latency_controlled_rerun": {
-    "note": "3 interleaved repetitions per variant, median ms/window; quiet box",
-    "fp32": {
-      "batch1_ms_per_window_median": 10.969150001983508,
-      "batch1_reps": [
-        10.969150001983508,
-        12.646450000829645,
-        10.49820000116597
-      ],
-      "batch64_ms_per_window_median": 2.2734187500077496,
-      "batch64_reps": [
-        2.377234374989712,
-        2.124126562478068,
-        2.2734187500077496
-      ]
-    },
-    "fp16": {
-      "batch1_ms_per_window_median": 24.313550000442774,
-      "batch1_reps": [
-        25.1078499986761,
-        21.856999999727122,
-        24.313550000442774
-      ],
-      "batch64_ms_per_window_median": 2.414695312495496,
-      "batch64_reps": [
-        2.5705156249955508,
-        1.7137437499741281,
-        2.414695312495496
-      ]
-    },
-    "int8_dynamic": {
-      "batch1_ms_per_window_median": 15.627150000000256,
-      "batch1_reps": [
-        17.67525000104797,
-        14.627999998992891,
-        15.627150000000256
-      ],
-      "batch64_ms_per_window_median": 2.0546906250160646,
-      "batch64_reps": [
-        2.0546906250160646,
-        2.03407343752815,
-        2.9325796875241394
-      ]
-    },
-    "onnx_fp32": {
-      "batch1_ms_per_window_median": 3.186650001225644,
-      "batch1_reps": [
-        2.7332500012562377,
-        3.1995500012271805,
-        3.186650001225644
-      ],
-      "batch64_ms_per_window_median": 1.9893374999924163,
-      "batch64_reps": [
-        1.5590843750032946,
-        1.9893374999924163,
-        2.2144343749914697
-      ]
-    },
-    "onnx_int8_ort_dynamic": {
-      "batch1_ms_per_window_median": 6.50984999811044,
-      "batch1_reps": [
-        6.50984999811044,
-        6.455249998907675,
-        6.789299999581999
-      ],
-      "batch64_ms_per_window_median": 5.770093750015803,
-      "batch64_reps": [
-        5.770093750015803,
-        3.912374999970325,
-        7.8067296875019565
-      ]
-    }
-  },
-  "onnx_static_ptq": {
-    "env": {
-      "onnxruntime": "1.26.0",
-      "torch": "2.12.0+cpu",
-      "platform": "Windows-11-10.0.26200-SP0",
-      "source_model": "retrained_fp32_dynamic.onnx",
-      "preprocessed_model": {
-        "file": "retrained_fp32_preproc.onnx",
-        "size_mb": 8.981529
-      }
-    },
-    "variants": {
-      "minmax_all": {
-        "file": "retrained_int8_static_minmax_all.onnx",
-        "size_bytes": 2604286,
-        "size_mb": 2.604286,
-        "calibration": {
-          "method": "minmax",
-          "windows": 1000,
-          "percentile": null,
-          "seconds": 5.052440166473389
-        },
-        "scope": "all",
-        "per_channel": true,
-        "activation_type": "QInt8",
-        "weight_type": "QInt8",
-        "node_counts": {
-          "Add": 9,
-          "AveragePool": 1,
-          "BatchNormalization": 12,
-          "Concat": 10,
-          "Conv": 43,
-          "DequantizeLinear": 283,
-          "Einsum": 4,
-          "Gather": 16,
-          "Mul": 39,
-          "QuantizeLinear": 181,
-          "Reshape": 14,
-          "Shape": 2,
-          "Sigmoid": 37,
-          "Slice": 8,
-          "Softmax": 2,
-          "Squeeze": 1,
-          "Transpose": 7,
-          "Unsqueeze": 11
-        },
-        "max_abs_diff_vs_fp32_fixture": 0.015945255756378174,
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.9545266661643982,
-          "pck@50": 0.9913666645050049,
-          "mpjpe": 0.014860070134699345,
-          "wall_seconds": 43.455235958099365
-        }
-      },
-      "minmax_conv": {
-        "file": "retrained_int8_static_minmax_conv.onnx",
-        "size_bytes": 2527421,
-        "size_mb": 2.527421,
-        "calibration": {
-          "method": "minmax",
-          "windows": 1000,
-          "percentile": null,
-          "seconds": 4.380746126174927
-        },
-        "scope": "conv",
-        "per_channel": true,
-        "activation_type": "QInt8",
-        "weight_type": "QInt8",
-        "node_counts": {
-          "Add": 9,
-          "AveragePool": 1,
-          "BatchNormalization": 12,
-          "Concat": 10,
-          "Conv": 43,
-          "DequantizeLinear": 156,
-          "Einsum": 4,
-          "Gather": 16,
-          "Mul": 39,
-          "QuantizeLinear": 78,
-          "Reshape": 14,
-          "Shape": 2,
-          "Sigmoid": 37,
-          "Slice": 8,
-          "Softmax": 2,
-          "Squeeze": 1,
-          "Transpose": 7,
-          "Unsqueeze": 11
-        },
-        "max_abs_diff_vs_fp32_fixture": 0.010693132877349854,
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.9663399996757507,
-          "pck@50": 0.9918666641235352,
-          "mpjpe": 0.01084446222037077,
-          "wall_seconds": 35.937947034835815
-        }
-      },
-      "entropy_all": {
-        "file": "retrained_int8_static_entropy_all.onnx",
-        "size_bytes": 2604268,
-        "size_mb": 2.604268,
-        "calibration": {
-          "method": "entropy",
-          "windows": 512,
-          "percentile": null,
-          "seconds": 23.835066318511963
-        },
-        "scope": "all",
-        "per_channel": true,
-        "activation_type": "QInt8",
-        "weight_type": "QInt8",
-        "node_counts": {
-          "Add": 9,
-          "AveragePool": 1,
-          "BatchNormalization": 12,
-          "Concat": 10,
-          "Conv": 43,
-          "DequantizeLinear": 283,
-          "Einsum": 4,
-          "Gather": 16,
-          "Mul": 39,
-          "QuantizeLinear": 181,
-          "Reshape": 14,
-          "Shape": 2,
-          "Sigmoid": 37,
-          "Slice": 8,
-          "Softmax": 2,
-          "Squeeze": 1,
-          "Transpose": 7,
-          "Unsqueeze": 11
-        },
-        "max_abs_diff_vs_fp32_fixture": 0.015280365943908691,
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.9530466662406921,
-          "pck@50": 0.9912600006103516,
-          "mpjpe": 0.015098519864678382,
-          "wall_seconds": 51.514281034469604
-        }
-      },
-      "entropy_conv": {
-        "file": "retrained_int8_static_entropy_conv.onnx",
-        "size_bytes": 2527403,
-        "size_mb": 2.527403,
-        "calibration": {
-          "method": "entropy",
-          "windows": 512,
-          "percentile": null,
-          "seconds": 9.634419918060303
-        },
-        "scope": "conv",
-        "per_channel": true,
-        "activation_type": "QInt8",
-        "weight_type": "QInt8",
-        "node_counts": {
-          "Add": 9,
-          "AveragePool": 1,
-          "BatchNormalization": 12,
-          "Concat": 10,
-          "Conv": 43,
-          "DequantizeLinear": 156,
-          "Einsum": 4,
-          "Gather": 16,
-          "Mul": 39,
-          "QuantizeLinear": 78,
-          "Reshape": 14,
-          "Shape": 2,
-          "Sigmoid": 37,
-          "Slice": 8,
-          "Softmax": 2,
-          "Squeeze": 1,
-          "Transpose": 7,
-          "Unsqueeze": 11
-        },
-        "max_abs_diff_vs_fp32_fixture": 0.012535125017166138,
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.9659599989891052,
-          "pck@50": 0.9918666648864746,
-          "mpjpe": 0.010778637571632861,
-          "wall_seconds": 41.01180171966553
-        }
-      },
-      "percentile_all": {
-        "file": "retrained_int8_static_percentile_all.onnx",
-        "size_bytes": 2604052,
-        "size_mb": 2.604052,
-        "calibration": {
-          "method": "percentile",
-          "windows": 512,
-          "percentile": 99.99,
-          "seconds": 20.221954584121704
-        },
-        "scope": "all",
-        "per_channel": true,
-        "activation_type": "QInt8",
-        "weight_type": "QInt8",
-        "node_counts": {
-          "Add": 9,
-          "AveragePool": 1,
-          "BatchNormalization": 12,
-          "Concat": 10,
-          "Conv": 43,
-          "DequantizeLinear": 283,
-          "Einsum": 4,
-          "Gather": 16,
-          "Mul": 39,
-          "QuantizeLinear": 181,
-          "Reshape": 14,
-          "Shape": 2,
-          "Sigmoid": 37,
-          "Slice": 8,
-          "Softmax": 2,
-          "Squeeze": 1,
-          "Transpose": 7,
-          "Unsqueeze": 11
-        },
-        "max_abs_diff_vs_fp32_fixture": 0.017689883708953857,
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.9639333323478698,
-          "pck@50": 0.9916799991607667,
-          "mpjpe": 0.012176512064039708,
-          "wall_seconds": 49.365190744400024
-        }
-      },
-      "percentile_conv": {
-        "file": "retrained_int8_static_percentile_conv.onnx",
-        "size_bytes": 2527241,
-        "size_mb": 2.527241,
-        "calibration": {
-          "method": "percentile",
-          "windows": 512,
-          "percentile": 99.99,
-          "seconds": 8.223475694656372
-        },
-        "scope": "conv",
-        "per_channel": true,
-        "activation_type": "QInt8",
-        "weight_type": "QInt8",
-        "node_counts": {
-          "Add": 9,
-          "AveragePool": 1,
-          "BatchNormalization": 12,
-          "Concat": 10,
-          "Conv": 43,
-          "DequantizeLinear": 156,
-          "Einsum": 4,
-          "Gather": 16,
-          "Mul": 39,
-          "QuantizeLinear": 78,
-          "Reshape": 14,
-          "Shape": 2,
-          "Sigmoid": 37,
-          "Slice": 8,
-          "Softmax": 2,
-          "Squeeze": 1,
-          "Transpose": 7,
-          "Unsqueeze": 11
-        },
-        "max_abs_diff_vs_fp32_fixture": 0.014725983142852783,
-        "accuracy": {
-          "samples": 10000,
-          "pck@20": 0.9660599988937378,
-          "pck@50": 0.9916066654205322,
-          "mpjpe": 0.010310938355326652,
-          "wall_seconds": 36.89548587799072
-        }
-      }
-    },
-    "latency": {
-      "note": "3 interleaved repetitions per variant, median ms/window; onnx_fp32 / onnx_int8_ort_dynamic are same-session references",
-      "onnx_fp32": {
-        "batch1_reps": [
-          4.5327999996516155,
-          2.535649999117595,
-          2.167549997466267
-        ],
-        "batch64_reps": [
-          1.9354515624740998,
-          2.4948054687854437,
-          1.9334703125082342
-        ],
-        "batch1_ms_per_window_median": 2.535649999117595,
-        "batch64_ms_per_window_median": 1.9354515624740998
-      },
-      "onnx_int8_ort_dynamic": {
-        "batch1_reps": [
-          5.698599999959697,
-          5.721350000385428,
-          4.805099997611251
-        ],
-        "batch64_reps": [
-          4.096601562508795,
-          4.857628124995017,
-          4.583800000006022
-        ],
-        "batch1_ms_per_window_median": 5.698599999959697,
-        "batch64_ms_per_window_median": 4.583800000006022
-      },
-      "entropy_all": {
-        "batch1_reps": [
-          6.444149999879301,
-          5.038299999796436,
-          5.713200000172947
-        ],
-        "batch64_reps": [
-          4.149468750028973,
-          3.437125000004926,
-          4.410960937491382
-        ],
-        "batch1_ms_per_window_median": 5.713200000172947,
-        "batch64_ms_per_window_median": 4.149468750028973
-      },
-      "entropy_conv": {
-        "batch1_reps": [
-          4.874750000453787,
-          5.169099998965976,
-          5.236699998931726
-        ],
-        "batch64_reps": [
-          3.010160156236452,
-          3.1175546875203963,
-          3.516850781238645
-        ],
-        "batch1_ms_per_window_median": 5.169099998965976,
-        "batch64_ms_per_window_median": 3.1175546875203963
-      },
-      "percentile_all": {
-        "batch1_reps": [
-          5.184749999898486,
-          5.2898499998264015,
-          5.916899999647285
-        ],
-        "batch64_reps": [
-          4.305105468745296,
-          4.460741406262514,
-          4.184502343747454
-        ],
-        "batch1_ms_per_window_median": 5.2898499998264015,
-        "batch64_ms_per_window_median": 4.305105468745296
-      },
-      "percentile_conv": {
-        "batch1_reps": [
-          4.916449999655015,
-          7.150899999032845,
-          5.284949998895172
-        ],
-        "batch64_reps": [
-          3.855813281262499,
-          4.688969531230214,
-          5.220103124997877
-        ],
-        "batch1_ms_per_window_median": 5.284949998895172,
-        "batch64_ms_per_window_median": 4.688969531230214
-      },
-      "minmax_all": {
-        "batch1_reps": [
-          6.463300000177696,
-          7.149449998905766,
-          5.3209000016067876
-        ],
-        "batch64_reps": [
-          3.9251343750095202,
-          4.033442187505898,
-          3.428199218745931
-        ],
-        "batch1_ms_per_window_median": 6.463300000177696,
-        "batch64_ms_per_window_median": 3.9251343750095202
-      },
-      "minmax_conv": {
-        "batch1_reps": [
-          5.9961499991914025,
-          5.236549999608542,
-          4.854399998293957
-        ],
-        "batch64_reps": [
-          4.368359375007458,
-          3.249617187492504,
-          3.0238906249735464
-        ],
-        "batch1_ms_per_window_median": 5.236549999608542,
-        "batch64_ms_per_window_median": 3.249617187492504
-      }
-    },
-    "accuracy_subset": {
-      "description": "seed-42 file-level 70/15/15 test split, corrupted windows excluded, seed-42 random subset (same as quantize_bench/eval_ort_accuracy)",
-      "subset_size": 10000
-    }
-  },
-  "tiny_variant": {
-    "env": {
-      "torch": "2.12.0+cpu",
-      "onnxruntime": "1.26.0",
-      "platform": "Windows-11-10.0.26200-SP0",
-      "num_threads": 16,
-      "checkpoint": "results\\tiny_best.pth",
-      "checkpoint_size_bytes": 340555,
-      "params": 56290,
-      "variant_config": {
-        "tcn": [
-          68,
-          56,
-          44,
-          32
-        ],
-        "conv": [
-          2,
-          4,
-          8,
-          16
-        ],
-        "attn_groups": 2,
-        "groups_mode": "depthwise",
-        "input_pw_groups": 4
-      }
-    },
-    "export": {
-      "mode": "dynamic-batch",
-      "exporter": "torchscript",
-      "opset": 17,
-      "file": "tiny_fp32_dynamic.onnx",
-      "size_bytes": 295279,
-      "size_mb": 0.295279,
-      "verified_batches": [
-        1,
-        2,
-        64
-      ],
-      "note": "AdaptiveAvgPool2d((15,1)) replaced at export by an exact mean(-1) + constant averaging matmul (final_width 16 is not a multiple of 15, which the TorchScript exporter rejects); exactness proven by the parity check vs the original torch model"
-    },
-    "parity": {
-      "fixture": "results/parity_fixture.npz input (batch 2, seed 42); reference output recomputed with the tiny torch model",
-      "max_abs_diff_vs_torch": 1.4901161193847656e-07,
-      "pass_lt_1e-4": true
-    },
-    "int8_static_percentile_conv": {
-      "file": "tiny_int8_static_percentile_conv.onnx",
-      "size_bytes": 248278,
-      "size_mb": 0.248278,
-      "calibration": {
-        "method": "percentile",
-        "percentile": 99.99,
-        "windows": 512,
-        "scope": "conv-only TRAIN-split corruption-free",
-        "seconds": 1.5347836017608643
-      },
-      "per_channel": true,
-      "activation_type": "QInt8",
-      "weight_type": "QInt8",
-      "max_abs_diff_vs_fp32_fixture": 0.018491357564926147
-    },
-    "latency": {
-      "note": "3 interleaved repetitions per variant, median ms/window; full-model sessions are same-session references",
-      "tiny_onnx_fp32": {
-        "batch1_reps": [
-          0.6312500008789357,
-          0.6834500018157996,
-          0.6595999984710943
-        ],
-        "batch64_reps": [
-          0.37747578119251557,
-          0.24196640623586063,
-          0.2314671875183194
-        ],
-        "batch1_ms_per_window_median": 0.6595999984710943,
-        "batch64_ms_per_window_median": 0.24196640623586063
-      },
-      "tiny_onnx_int8_static_percentile_conv": {
-        "batch1_reps": [
-          0.7988500001374632,
-          0.9382499993080273,
-          0.8451000030618161
-        ],
-        "batch64_reps": [
-          0.9211476562995813,
-          1.3045390625165965,
-          1.026230468767153
-        ],
-        "batch1_ms_per_window_median": 0.8451000030618161,
-        "batch64_ms_per_window_median": 1.026230468767153
-      },
-      "full_onnx_fp32_reference": {
-        "batch1_reps": [
-          2.267249998112675,
-          2.80170000041835,
-          2.132149998942623
-        ],
-        "batch64_reps": [
-          1.3050578124875756,
-          1.4244992187855132,
-          1.8014164062947202
-        ],
-        "batch1_ms_per_window_median": 2.267249998112675,
-        "batch64_ms_per_window_median": 1.4244992187855132
-      },
-      "full_onnx_int8_static_percentile_conv_reference": {
-        "batch1_reps": [
-          5.529599999135826,
-          4.768399998283712,
-          6.215800000063609
-        ],
-        "batch64_reps": [
-          3.815724218725336,
-          3.1025562500417436,
-          4.333318749957016
-        ],
-        "batch1_ms_per_window_median": 5.529599999135826,
-        "batch64_ms_per_window_median": 3.815724218725336
-      }
-    },
-    "accuracy_subset": {
-      "description": "seed-42 file-level 70/15/15 test split, corrupted windows excluded, seed-42 random subset (same as quantize_bench/eval_ort_accuracy/static_ptq_bench)",
-      "subset_size": 10000
-    },
-    "accuracy": {
-      "tiny_onnx_fp32": {
-        "samples": 10000,
-        "pck@20": 0.941106667804718,
-        "pck@50": 0.99369333152771,
-        "mpjpe": 0.012527281279861927,
-        "wall_seconds": 10.927234888076782
-      },
-      "tiny_onnx_int8_static_percentile_conv": {
-        "samples": 10000,
-        "pck@20": 0.9268133331298828,
-        "pck@50": 0.9932933319091797,
-        "mpjpe": 0.014906252065300942,
-        "wall_seconds": 12.320892333984375
-      }
-    }
-  }
-}
@@ -1,3 +0,0 @@
-{"variant": "half", "params": 843834, "tcn_channels": [270, 220, 170, 120], "conv_channels": [4, 8, 16, 32], "attn_groups": 4, "groups_mode": "gcd20", "input_pw_groups": 1, "tcn_groups_per_block": [[20, 10], [10, 20], [20, 10], [10, 20]], "conv_strides": [2, 2, 2, 1], "final_width": 15, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 28, "best_epoch": 23, "best_val_mpjpe": 0.008576328293592842, "best_val_pck20": 0.9690593021534107, "train_seconds": 1346.4, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T03:09:47Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/half_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.009419974447676428, "pck@10": 0.8740543655289544, "pck@20": 0.9610469643628156, "pck@30": 0.9813556064146537, "pck@40": 0.9896086878246731, "pck@50": 0.9934827546013726}, "test_clean": {"samples": 52560, "mpjpe": 0.008980081718602137, "pck@10": 0.8840944136840205, "pck@20": 0.9662253179869514, "pck@30": 0.9847971080282144, "pck@40": 0.9917795997050618, "pck@50": 0.9946956242600532}}
-{"variant": "quarter", "params": 338600, "tcn_channels": [135, 110, 85, 60], "conv_channels": [2, 4, 8, 16], "attn_groups": 2, "groups_mode": "gcd20", "input_pw_groups": 1, "tcn_groups_per_block": [[20, 5], [5, 10], [10, 5], [5, 20]], "conv_strides": [2, 2, 1, 1], "final_width": 15, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 50, "best_epoch": 50, "best_val_mpjpe": 0.008780752391864856, "best_val_pck20": 0.9672531302240159, "train_seconds": 1754.4, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T03:39:06Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/quarter_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.009705399298005634, "pck@10": 0.8646123917014511, "pck@20": 0.9553815319449813, "pck@30": 0.979827209190086, "pck@40": 0.9887037501511751, "pck@50": 0.9931309027671814}, "test_clean": {"samples": 52560, "mpjpe": 0.009279253277105465, "pck@10": 0.8742288637923323, "pck@20": 0.9605315079427745, "pck@30": 0.9833016723076865, "pck@40": 0.9908206971631566, "pck@50": 0.9942719799017071}}
-{"variant": "tiny", "params": 56290, "tcn_channels": [68, 56, 44, 32], "conv_channels": [2, 4, 8, 16], "attn_groups": 2, "groups_mode": "depthwise", "input_pw_groups": 4, "tcn_groups_per_block": [[540, 68], [68, 56], [56, 44], [44, 32]], "conv_strides": [2, 1, 1, 1], "final_width": 16, "batch_size": 64, "max_epochs": 50, "patience": 5, "lr": 0.0001, "weight_decay": 5e-05, "seed": 42, "precision": "fp32", "epochs_run": 50, "best_epoch": 47, "best_val_mpjpe": 0.012602971208592256, "best_val_pck20": 0.9397210340146666, "train_seconds": 1540.1, "torch": "2.11.0+cu128", "error": null, "finished_utc": "2026-06-11T04:04:50Z", "checkpoint": "/home/ruvultra/wiflow-std-bench/sweep/tiny_best.pth", "test_full": {"samples": 54000, "mpjpe": 0.012859782406853305, "pck@10": 0.7640358444319831, "pck@20": 0.9364815320968628, "pck@30": 0.9731568422317505, "pck@40": 0.9866444962642811, "pck@50": 0.992488939108672}, "test_clean": {"samples": 52560, "mpjpe": 0.012502924276904246, "pck@10": 0.770895526488985, "pck@20": 0.9411073559313967, "pck@30": 0.9764840687790962, "pck@40": 0.9886695077067278, "pck@50": 0.9936238432039409}}
@@ -1,21 +0,0 @@
-{
-  "checkpoint": "/home/ruvultra/wiflow-std-bench/upstream/test/best_pose_model.pth",
-  "test_full": {
-    "samples": 54000,
-    "mpjpe": 0.009834060806367133,
-    "pck@10": 0.8686346120127925,
-    "pck@20": 0.9608815324571398,
-    "pck@30": 0.9789111610695168,
-    "pck@40": 0.9857975759682832,
-    "pck@50": 0.9898827553325229
-  },
-  "test_clean": {
-    "samples": 52560,
-    "mpjpe": 0.009432755044379373,
-    "pck@10": 0.876996495807189,
-    "pck@20": 0.9661454100405608,
-    "pck@30": 0.9823453060205306,
-    "pck@40": 0.987909734176537,
-    "pck@50": 0.9911238361167036
-  }
-}
@@ -1,32 +0,0 @@
-{
-  "published": {
-    "pck@20": 0.9725,
-    "pck@30": 0.9863,
-    "pck@40": 0.9916,
-    "pck@50": 0.9948,
-    "mpjpe": 0.007
-  },
-  "params_millions": 2.225042,
-  "data_dir": "C:\\Users\\ruv\\.cache\\kagglehub\\datasets\\kaka2434\\wiflow-dataset\\versions\\1\\preprocessed_csi_data",
-  "device": "cpu",
-  "test_full": {
-    "samples": 54000,
-    "mpjpe": NaN,
-    "pck@10": 5.6790124349020145e-05,
-    "pck@20": 0.0007876543271596785,
-    "pck@30": 0.007780246982971827,
-    "pck@40": 0.05529259262923841,
-    "pck@50": 0.1542370371548114,
-    "wall_seconds": 118.03756999969482
-  },
-  "test_drop_last": {
-    "samples": 53952,
-    "mpjpe": NaN,
-    "pck@10": 5.6840649370682976e-05,
-    "pck@20": 0.0007883550872372227,
-    "pck@30": 0.007787168910892621,
-    "pck@40": 0.055318307667895535,
-    "pck@50": 0.15425316342412276,
-    "wall_seconds": 120.87458372116089
-  }
-}
@@ -1,333 +0,0 @@
-"""ADR-152 edge optimization follow-up: ONNX Runtime STATIC post-training
-quantization (calibration-based QDQ) of the retrained WiFlow-STD model, to
-improve on the dynamic-int8 result (2.44 MB, PCK@20 96.52%, 6.5 ms/win b1).
-
-Static PTQ pre-computes activation ranges from calibration data, so inference
-uses QLinearConv/QDQ kernels instead of dynamic ConvInteger -- typically both
-faster and (with good calibration) closer to fp32 accuracy.
-
-Method:
-  - Calibration set: corruption-free windows drawn ONLY from the seed-42
-    file-level TRAINING split (same split as eval_repro.py; corrupted windows
-    excluded via results/nan_windows_mask.npy | big_windows_mask.npy), chosen
-    with np.random.default_rng(42). Never test windows.
-  - quantize_static, QuantFormat.QDQ, per-channel int8 weights, int8
-    activations; calibration methods MinMax / Entropy / Percentile(99.99);
-    scopes "all" (ORT default op set) vs "conv" (op_types_to_quantize=
-    ["Conv"] -- leaves the attention path, which exports as Einsum/Softmax
-    and elementwise ops, in fp32).
-  - Model is pre-processed first (quant_pre_process: symbolic shape
-    inference + ORT graph optimization, folds BatchNormalization into Conv).
-  - Accuracy: identical protocol to eval_ort_accuracy.py -- the 10,000-window
-    seed-42 subset of the corruption-free test split (PCK@20/50, MPJPE).
-  - Latency: median ms/window at batch 1 (100 runs) and batch 64 (30 runs),
-    3 interleaved repetitions across all variants (fp32 and dynamic-int8
-    sessions included as same-session reference points).
-
-Usage:
-  PYTHONUTF8=1 .venv/Scripts/python.exe static_ptq_bench.py \
-      [--data-dir <preprocessed_csi_data>] [--subset 10000]
-      [--calib-minmax 1000] [--calib-hist 512] [--skip-accuracy]
-
-Writes/merges into results/edge_optimization.json under key "onnx_static_ptq".
-"""
-
-import argparse
-import collections
-import json
-import os
-import platform
-import statistics
-import sys
-import time
-
-import numpy as np
-import torch
-
-HERE = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, HERE)
-
-from _bench_common import RESULTS  # noqa: E402
-# quantize_bench sets up upstream imports + the np.load mmap patch
-# (both via _bench_common.import_upstream)
-from quantize_bench import build_test_subset  # noqa: E402
-import quantize_bench as qb  # noqa: E402
-from eval_ort_accuracy import evaluate_ort  # noqa: E402
-
-FP32_ONNX = os.path.join(RESULTS, "retrained_fp32_dynamic.onnx")
-DYN_INT8_ONNX = os.path.join(RESULTS, "retrained_int8_ort_dynamic.onnx")
-PREPROC_ONNX = os.path.join(RESULTS, "retrained_fp32_preproc.onnx")
-
-
-# ---------------------------------------------------------------------------
-# calibration data: corruption-free TRAINING-split windows only
-# ---------------------------------------------------------------------------
-
-def build_calibration_windows(data_dir, n_windows):
-    """Seed-42 file-level 70/15/15 TRAIN split (exactly as eval_repro.py),
-    minus corrupted windows, then a seed-42 random draw of n_windows."""
-    dataset = qb.PreprocessedCSIKeypointsDataset(
-        data_dir=data_dir, keypoint_scale=1000.0, enable_temporal_clean=True)
-    train_loader, _va, _te = qb.create_preprocessed_train_val_test_loaders(
-        dataset=dataset, batch_size=64, num_workers=0, random_seed=42)
-    train_indices = np.asarray(train_loader.dataset.indices)
-
-    corrupted = (np.load(os.path.join(RESULTS, "nan_windows_mask.npy"))
-                 | np.load(os.path.join(RESULTS, "big_windows_mask.npy")))
-    clean = train_indices[~corrupted[train_indices]]
-    print(f"train split: {len(train_indices)} windows, "
-          f"{len(train_indices) - len(clean)} corrupted excluded, "
-          f"{len(clean)} clean")
-
-    rng = np.random.default_rng(42)
-    sel = np.sort(rng.choice(clean, size=n_windows, replace=False))
-    xs = np.stack([dataset[int(i)][0].numpy() for i in sel]).astype(np.float32)
-    print(f"calibration tensor: {xs.shape} from {n_windows} clean TRAIN windows")
-    return xs
-
-
-def make_reader(windows, batch_size=64):
-    from onnxruntime.quantization import CalibrationDataReader
-
-    class WindowReader(CalibrationDataReader):
-        def __init__(self):
-            self._batches = [windows[i:i + batch_size]
-                             for i in range(0, len(windows), batch_size)]
-            self._it = iter(self._batches)
-
-        def get_next(self):
-            b = next(self._it, None)
-            return None if b is None else {"input": b}
-
-        def rewind(self):
-            self._it = iter(self._batches)
-
-        def __len__(self):
-            return len(self._batches)
-
-    return WindowReader()
-
-
-# ---------------------------------------------------------------------------
-# quantization variants
-# ---------------------------------------------------------------------------
-
-def preprocess_model():
-    from onnxruntime.quantization.shape_inference import quant_pre_process
-    quant_pre_process(FP32_ONNX, PREPROC_ONNX)
-    return PREPROC_ONNX
-
-
-def quantize_variant(src, dst, method, scope, calib_windows):
-    from onnxruntime.quantization import (CalibrationMethod, QuantFormat,
-                                          QuantType, quantize_static)
-    methods = {
-        "minmax": CalibrationMethod.MinMax,
-        "entropy": CalibrationMethod.Entropy,
-        "percentile": CalibrationMethod.Percentile,
-    }
-    # NB: do NOT pass CalibMaxIntermediateOutputs -- in ORT 1.26 the MinMax
-    # calibrater clears its buffer every N batches and then raises
-    # "No data is collected" if the batch count is divisible by N.
-    extra = {}
-    if method == "percentile":
-        extra["CalibPercentile"] = 99.99
-    op_types = ["Conv"] if scope == "conv" else None
-
-    t0 = time.time()
-    quantize_static(
-        src, dst, make_reader(calib_windows),
-        quant_format=QuantFormat.QDQ,
-        op_types_to_quantize=op_types,
-        per_channel=True,
-        activation_type=QuantType.QInt8,
-        weight_type=QuantType.QInt8,
-        calibrate_method=methods[method],
-        extra_options=extra,
-    )
-    secs = time.time() - t0
-
-    import onnx
-    ops = collections.Counter(n.op_type for n in onnx.load(dst).graph.node)
-    return {
-        "file": os.path.basename(dst),
-        "size_bytes": os.path.getsize(dst),
-        "size_mb": os.path.getsize(dst) / 1e6,
-        "calibration": {"method": method,
-                        "windows": int(len(calib_windows)),
-                        "percentile": extra.get("CalibPercentile"),
-                        "seconds": secs},
-        "scope": scope,
-        "per_channel": True,
-        "activation_type": "QInt8",
-        "weight_type": "QInt8",
-        "node_counts": {k: v for k, v in sorted(ops.items())},
-    }
-
-
-# ---------------------------------------------------------------------------
-# latency (3 interleaved reps, like the latency_controlled_rerun)
-# ---------------------------------------------------------------------------
-
-def ort_session(path):
-    import onnxruntime as ort
-    return ort.InferenceSession(path, providers=["CPUExecutionProvider"])
-
-
-def bench_ort(sess, batch, n_runs):
-    rng = np.random.default_rng(123)
-    x = rng.random((batch, 540, 20), dtype=np.float32)
-    inp = sess.get_inputs()[0].name
-    for _ in range(max(5, n_runs // 10)):
-        sess.run(None, {inp: x})
-    times = []
-    for _ in range(n_runs):
-        t0 = time.perf_counter()
-        sess.run(None, {inp: x})
-        times.append(time.perf_counter() - t0)
-    return statistics.median(times) * 1e3 / batch  # ms/window
-
-
-def interleaved_latency(sessions, reps=3, runs_b1=100, runs_b64=30):
-    lat = {name: {"batch1_reps": [], "batch64_reps": []} for name in sessions}
-    for rep in range(reps):
-        for name, sess in sessions.items():
-            lat[name]["batch1_reps"].append(bench_ort(sess, 1, runs_b1))
-            lat[name]["batch64_reps"].append(bench_ort(sess, 64, runs_b64))
-            print(f"  rep {rep + 1}/{reps} {name}: "
-                  f"b1={lat[name]['batch1_reps'][-1]:.2f} "
-                  f"b64={lat[name]['batch64_reps'][-1]:.3f} ms/win", flush=True)
-    for name in lat:
-        lat[name]["batch1_ms_per_window_median"] = statistics.median(
-            lat[name]["batch1_reps"])
-        lat[name]["batch64_ms_per_window_median"] = statistics.median(
-            lat[name]["batch64_reps"])
-    return lat
-
-
-# ---------------------------------------------------------------------------
-
-def main():
-    import onnxruntime
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--data-dir", default=os.path.join(
-        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
-        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
-    parser.add_argument("--subset", type=int, default=10000)
-    parser.add_argument("--calib-minmax", type=int, default=1000)
-    parser.add_argument("--calib-hist", type=int, default=512,
-                        help="calibration windows for Entropy/Percentile "
-                             "(histogram calibraters hold all intermediate "
-                             "activations in RAM)")
-    parser.add_argument("--skip-accuracy", action="store_true")
-    parser.add_argument("--methods", default="minmax,entropy,percentile",
-                        help="comma list of calibration methods to (re)run; "
-                             "results merge into existing onnx_static_ptq")
-    parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
-    args = parser.parse_args()
-
-    results = {
-        "env": {
-            "onnxruntime": onnxruntime.__version__,
-            "torch": torch.__version__,
-            "platform": platform.platform(),
-            "source_model": os.path.basename(FP32_ONNX),
-        },
-        "variants": {},
-    }
-
-    # ---- calibration data (TRAIN split only) -------------------------------
-    calib_mm = build_calibration_windows(args.data_dir, args.calib_minmax)
-    calib_hist = calib_mm[:args.calib_hist]
-
-    # ---- preprocess + quantize ---------------------------------------------
-    print("\n=== quant_pre_process (shape inference + graph optimization) ===")
-    src = preprocess_model()
-    results["env"]["preprocessed_model"] = {
-        "file": os.path.basename(src),
-        "size_mb": os.path.getsize(src) / 1e6,
-    }
-
-    matrix = [(m, s) for m in args.methods.split(",")
-              for s in ("all", "conv")]
-    for method, scope in matrix:
-        name = f"{method}_{scope}"
-        dst = os.path.join(RESULTS, f"retrained_int8_static_{name}.onnx")
-        calib = calib_mm if method == "minmax" else calib_hist
-        print(f"\n=== quantize_static: {name} "
-              f"({len(calib)} calib windows) ===", flush=True)
-        try:
-            results["variants"][name] = quantize_variant(
-                src, dst, method, scope, calib)
-            print(f"  {results['variants'][name]['size_mb']:.3f} MB")
-        except Exception as e:  # noqa: BLE001
-            results["variants"][name] = {"error": f"{type(e).__name__}: {e}"}
-            print(f"  FAILED: {e}")
-
-    # ---- fixture parity (sanity, batch 2) ----------------------------------
-    fixture = np.load(os.path.join(RESULTS, "parity_fixture.npz"))
-    fx, fy = fixture["input"], fixture["output"]
-    sessions = {}
-    for name, info in results["variants"].items():
-        if "error" in info:
-            continue
-        path = os.path.join(RESULTS, info["file"])
-        try:
-            sess = ort_session(path)
-            yq = sess.run(None, {sess.get_inputs()[0].name: fx})[0]
-            info["max_abs_diff_vs_fp32_fixture"] = float(np.abs(yq - fy).max())
-            sessions[name] = sess
-        except Exception as e:  # noqa: BLE001
-            info["run_error"] = f"{type(e).__name__}: {e}"
-    print("\nfixture max-abs-diff vs fp32:",
-          {n: round(results["variants"][n].get("max_abs_diff_vs_fp32_fixture",
-                                               float("nan")), 5)
-           for n in results["variants"]})
-
-    # ---- latency: 3 interleaved reps incl. fp32 + dynamic-int8 reference ----
-    print("\n=== latency (3 interleaved reps) ===")
-    lat_sessions = {"onnx_fp32": ort_session(FP32_ONNX),
-                    "onnx_int8_ort_dynamic": ort_session(DYN_INT8_ONNX)}
-    lat_sessions.update(sessions)
-    results["latency"] = {
-        "note": "3 interleaved repetitions per variant, median ms/window; "
-                "onnx_fp32 / onnx_int8_ort_dynamic are same-session references",
-        **interleaved_latency(lat_sessions),
-    }
-
-    # ---- accuracy on the standard 10k corruption-free test subset ----------
-    if not args.skip_accuracy:
-        loader, n_clean = build_test_subset(args.data_dir, args.subset)
-        results["accuracy_subset"] = {
-            "description": "seed-42 file-level 70/15/15 test split, corrupted "
-                           "windows excluded, seed-42 random subset (same as "
-                           "quantize_bench/eval_ort_accuracy)",
-            "subset_size": min(args.subset, n_clean) if args.subset else n_clean,
-        }
-        for name, sess in sessions.items():
-            print(f"\n=== accuracy: {name} ===")
-            results["variants"][name]["accuracy"] = evaluate_ort(
-                sess, loader, name)
-            print(json.dumps(results["variants"][name]["accuracy"], indent=2))
-
-    # ---- merge into edge_optimization.json ----------------------------------
-    merged = {}
-    if os.path.exists(args.out):
-        with open(args.out) as f:
-            merged = json.load(f)
-    prev = merged.get("onnx_static_ptq")
-    if prev:  # nested merge so partial --methods reruns don't clobber
-        prev["env"] = results["env"]
-        prev["variants"].update(results["variants"])
-        prev.setdefault("latency", {}).update(results["latency"])
-        if "accuracy_subset" in results:
-            prev["accuracy_subset"] = results["accuracy_subset"]
-    else:
-        merged["onnx_static_ptq"] = results
-    with open(args.out, "w") as f:
-        json.dump(merged, f, indent=2)
-    print(f"\nwrote {args.out}")
-
-
-if __name__ == "__main__":
-    main()
@@ -1,313 +0,0 @@
-"""ADR-152 efficiency-sweep follow-up: edge pipeline for the TINY compact
-WiFlow-STD variant (56,290 params, results/tiny_best.pth, trained overnight
-2026-06-10/11 -- see RESULTS.md "Efficiency sweep").
-
-Headline question: what does the smallest deployable WiFlow-class model look
-like (KB + ms + PCK)? Reuses the onnx_bench.py / static_ptq_bench.py
-machinery on the tiny checkpoint:
-
-  1. Load tiny_best.pth with remote/sweep/model_compact.py
-     (depthwise TCN groups, input_pw_groups=4, conv [2,4,8,16], attn groups 2).
-  2. Export ONNX: dynamic batch, opset 17, TorchScript exporter (dynamo=False)
-     -- same recipe that worked for the full model; verified at batch 1/2/64.
-     One forced deviation: tiny's stride schedule [2,1,1,1] leaves final_width
-     16, and the TorchScript exporter cannot export AdaptiveAvgPool2d((15,1))
-     when 15 is not a factor of the input height (the full model never hit
-     this -- its width was exactly 15). The adaptive pool over a fixed-size
-     feature map is a fixed linear map, so the export wrapper replaces it with
-     an exact matmul equivalent (PyTorch adaptive-pool bin semantics:
-     bin i averages rows floor(i*H/K)..ceil((i+1)*H/K)); the W axis (20->1,
-     a factor) becomes mean(-1). Exactness is proven by the parity check
-     below, which compares against the ORIGINAL torch model with the real
-     AdaptiveAvgPool2d.
-  3. Torch-vs-ORT parity on the stored fixture input
-     (results/parity_fixture.npz, batch 2, seed 42 -- same 540x20 input layout;
-     reference output recomputed with the tiny torch model). PASS < 1e-4.
-  4. Static QDQ conv-only int8 (quant_pre_process + quantize_static,
-     per-channel QInt8 weights+activations, Percentile(99.99) calibration on
-     512 corruption-free TRAIN-split windows -- the winning recipe and
-     calibration count from static_ptq_bench.py. 512, not "about 500":
-     ORT 1.26's histogram collector np.asarray()'s the per-batch maxima, so
-     the calibration count must be a multiple of the batch size 64 or the
-     ragged last batch crashes it).
-  5. Disk size + CPU latency b1/b64 (3 interleaved reps, median ms/window)
-     for tiny fp32 + tiny int8, with the full-model ONNX fp32 + static-int8
-     sessions interleaved as same-session references.
-  6. Accuracy (PCK@20/50 + MPJPE) on the identical 10k-window seed-42
-     corruption-free test subset for tiny fp32 + tiny int8.
-
-Usage:
-  PYTHONUTF8=1 .venv/Scripts/python.exe tiny_edge_bench.py \
-      [--data-dir <preprocessed_csi_data>] [--subset 10000] [--calib 512]
-  (--calib must be a multiple of 64; see step 4 above)
-
-Writes/merges into results/edge_optimization.json under key "tiny_variant".
-"""
-
-import argparse
-import json
-import os
-import platform
-import sys
-import time
-
-import numpy as np
-import torch
-
-HERE = os.path.dirname(os.path.abspath(__file__))
-RESULTS = os.path.join(HERE, "results")
-sys.path.insert(0, HERE)
-sys.path.insert(0, os.path.join(HERE, "remote", "sweep"))
-
-# quantize_bench sets up upstream imports + the np.load mmap patch
-from quantize_bench import build_test_subset  # noqa: E402
-from eval_ort_accuracy import evaluate_ort  # noqa: E402
-from static_ptq_bench import (  # noqa: E402
-    build_calibration_windows,
-    interleaved_latency,
-    make_reader,
-    ort_session,
-)
-from model_compact import CompactWiFlowPoseModel, describe  # noqa: E402
-
-TINY_CKPT = os.path.join(RESULTS, "tiny_best.pth")
-TINY_FP32_ONNX = os.path.join(RESULTS, "tiny_fp32_dynamic.onnx")
-TINY_PREPROC_ONNX = os.path.join(RESULTS, "tiny_fp32_preproc.onnx")
-TINY_INT8_ONNX = os.path.join(RESULTS, "tiny_int8_static_percentile_conv.onnx")
-FULL_FP32_ONNX = os.path.join(RESULTS, "retrained_fp32_dynamic.onnx")
-FULL_INT8_ONNX = os.path.join(RESULTS, "retrained_int8_static_percentile_conv.onnx")
-
-# Exact tiny config from remote/sweep/run_sweep.py VARIANTS (measured 56,290
-# params, clean-test PCK@20 94.11% -- results/efficiency_sweep.jsonl).
-TINY = dict(tcn=[68, 56, 44, 32], conv=[2, 4, 8, 16], attn_groups=2,
-            groups_mode="depthwise", input_pw_groups=4)
-
-
-def load_tiny_model():
-    model = CompactWiFlowPoseModel(
-        tcn_channels=TINY["tcn"], conv_channels=TINY["conv"],
-        attn_groups=TINY["attn_groups"], groups_mode=TINY["groups_mode"],
-        input_pw_groups=TINY["input_pw_groups"], dropout=0.5)
-    state = torch.load(TINY_CKPT, map_location="cpu", weights_only=True)
-    model.load_state_dict(state, strict=True)
-    model.eval()
-    return model
-
-
-def adaptive_pool_matrix(h_in, h_out):
-    """Exact AdaptiveAvgPool1d as a (h_out, h_in) averaging matrix, using
-    PyTorch's bin rule: bin i covers rows floor(i*h_in/h_out) ..
-    ceil((i+1)*h_in/h_out)."""
-    w = torch.zeros(h_out, h_in)
-    for i in range(h_out):
-        s = (i * h_in) // h_out
-        e = -((-(i + 1) * h_in) // h_out)  # ceil division
-        w[i, s:e] = 1.0 / (e - s)
-    return w
-
-
-class ExportWrapper(torch.nn.Module):
-    """CompactWiFlowPoseModel forward with the AdaptiveAvgPool2d((K,1))
-    replaced by an exact fixed linear map (mean over the factor W axis, then
-    a constant averaging matmul over the non-factor H axis) so the
-    TorchScript ONNX exporter accepts it. Bit-equivalent up to float
-    round-off; proven by the parity check against the original model."""
-
-    def __init__(self, m, num_keypoints=15):
-        super().__init__()
-        self.m = m
-        self.register_buffer(
-            "pool_w_t", adaptive_pool_matrix(m.final_width, num_keypoints).t())
-
-    def forward(self, x):
-        m = self.m
-        x = m.tcn(x)
-        x = x.transpose(1, 2).unsqueeze(1)
-        x = m.up(x)
-        for block in m.residual_blocks:
-            x = block(x)
-        x = x.permute(0, 1, 3, 2)
-        x = m.attention(x)
-        x = m.decoder(x)                  # [B, 2, H=final_width, T=20]
-        x = x.mean(-1)                    # W-axis pool (20 -> 1, a factor)
-        x = x.matmul(self.pool_w_t)       # exact adaptive H pool: [B, 2, K]
-        return x.transpose(1, 2)          # [B, K, 2]
-
-
-def export_onnx(model):
-    """Dynamic-batch TorchScript export (the recipe that worked for the full
-    model in onnx_bench.py), verified at batch 1/2/64. Uses ExportWrapper
-    (see docstring) because final_width 16 is not a multiple of 15."""
-    wrapper = ExportWrapper(model).eval()
-    x = torch.rand(2, 540, 20)
-    with torch.no_grad():
-        torch.onnx.export(
-            wrapper, (x,), TINY_FP32_ONNX, opset_version=17,
-            input_names=["input"], output_names=["output"], dynamo=False,
-            dynamic_axes={"input": {0: "batch"}, "output": {0: "batch"}})
-    sess = ort_session(TINY_FP32_ONNX)
-    inp = sess.get_inputs()[0].name
-    for b in (1, 2, 64):
-        y = sess.run(None, {inp: np.zeros((b, 540, 20), dtype=np.float32)})[0]
-        assert y.shape == (b, 15, 2), y.shape
-    return {
-        "mode": "dynamic-batch", "exporter": "torchscript", "opset": 17,
-        "file": os.path.basename(TINY_FP32_ONNX),
-        "size_bytes": os.path.getsize(TINY_FP32_ONNX),
-        "size_mb": os.path.getsize(TINY_FP32_ONNX) / 1e6,
-        "verified_batches": [1, 2, 64],
-        "note": "AdaptiveAvgPool2d((15,1)) replaced at export by an exact "
-                "mean(-1) + constant averaging matmul (final_width 16 is not "
-                "a multiple of 15, which the TorchScript exporter rejects); "
-                "exactness proven by the parity check vs the original torch "
-                "model",
-    }
-
-
-def quantize_tiny(calib_windows):
-    """quant_pre_process + static QDQ conv-only Percentile(99.99) int8 --
-    the winning recipe from static_ptq_bench.py."""
-    from onnxruntime.quantization import (CalibrationMethod, QuantFormat,
-                                          QuantType, quantize_static)
-    from onnxruntime.quantization.shape_inference import quant_pre_process
-
-    quant_pre_process(TINY_FP32_ONNX, TINY_PREPROC_ONNX)
-    t0 = time.time()
-    quantize_static(
-        TINY_PREPROC_ONNX, TINY_INT8_ONNX, make_reader(calib_windows),
-        quant_format=QuantFormat.QDQ,
-        op_types_to_quantize=["Conv"],
-        per_channel=True,
-        activation_type=QuantType.QInt8,
-        weight_type=QuantType.QInt8,
-        calibrate_method=CalibrationMethod.Percentile,
-        extra_options={"CalibPercentile": 99.99},
-    )
-    return {
-        "file": os.path.basename(TINY_INT8_ONNX),
-        "size_bytes": os.path.getsize(TINY_INT8_ONNX),
-        "size_mb": os.path.getsize(TINY_INT8_ONNX) / 1e6,
-        "calibration": {"method": "percentile", "percentile": 99.99,
-                        "windows": int(len(calib_windows)),
-                        "scope": "conv-only TRAIN-split corruption-free",
-                        "seconds": time.time() - t0},
-        "per_channel": True,
-        "activation_type": "QInt8",
-        "weight_type": "QInt8",
-    }
-
-
-def main():
-    import onnxruntime
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--data-dir", default=os.path.join(
-        os.path.expanduser("~"), ".cache", "kagglehub", "datasets", "kaka2434",
-        "wiflow-dataset", "versions", "1", "preprocessed_csi_data"))
-    parser.add_argument("--subset", type=int, default=10000)
-    parser.add_argument("--calib", type=int, default=512,
-                        help="calibration windows; must be a multiple of the "
-                             "64-window calibration batch (ORT histogram "
-                             "collector rejects ragged batches)")
-    parser.add_argument("--skip-accuracy", action="store_true")
-    parser.add_argument("--out", default=os.path.join(RESULTS, "edge_optimization.json"))
-    args = parser.parse_args()
-
-    if args.calib % 64 != 0:
-        parser.error(
-            f"--calib must be a multiple of 64 (got {args.calib}): ORT 1.26's "
-            f"histogram calibration collector np.asarray()'s the per-batch "
-            f"maxima and crashes on a ragged final batch (calibration batch "
-            f"size is 64)")
-
-    model = load_tiny_model()
-    info = describe(model)
-    print(f"tiny model: {info['params']:,} params, tcn_groups={info['tcn_groups_per_block']}, "
-          f"strides={info['conv_strides']}, final_width={info['final_width']}")
-    assert info["params"] == 56290, info["params"]
-
-    results = {
-        "env": {
-            "torch": torch.__version__,
-            "onnxruntime": onnxruntime.__version__,
-            "platform": platform.platform(),
-            "num_threads": torch.get_num_threads(),
-            "checkpoint": os.path.relpath(TINY_CKPT, HERE),
-            "checkpoint_size_bytes": os.path.getsize(TINY_CKPT),
-            "params": info["params"],
-            "variant_config": TINY,
-        },
-    }
-
-    # ---- export + parity ----------------------------------------------------
-    print("\n=== ONNX export (dynamic batch, opset 17, torchscript) ===")
-    results["export"] = export_onnx(model)
-    print(f"  {results['export']['size_mb']:.3f} MB, batches {results['export']['verified_batches']} OK")
-
-    fixture = np.load(os.path.join(RESULTS, "parity_fixture.npz"))
-    fx = fixture["input"]  # (2, 540, 20), seed 42 -- same input layout as full model
-    sess_fp32 = ort_session(TINY_FP32_ONNX)
-    y_ort = sess_fp32.run(None, {sess_fp32.get_inputs()[0].name: fx})[0]
-    with torch.no_grad():
-        y_torch = model(torch.from_numpy(fx)).numpy()
-    results["parity"] = {
-        "fixture": "results/parity_fixture.npz input (batch 2, seed 42); "
-                   "reference output recomputed with the tiny torch model",
-        "max_abs_diff_vs_torch": float(np.abs(y_ort - y_torch).max()),
-        "pass_lt_1e-4": bool(np.abs(y_ort - y_torch).max() < 1e-4),
-    }
-    print("parity:", json.dumps(results["parity"], indent=2))
-    assert results["parity"]["pass_lt_1e-4"], "torch-vs-ORT parity FAILED"
-
-    # ---- static PTQ int8 ------------------------------------------------------
-    print(f"\n=== static QDQ int8 (Percentile conv-only, {args.calib} calib windows) ===")
-    calib = build_calibration_windows(args.data_dir, args.calib)
-    results["int8_static_percentile_conv"] = quantize_tiny(calib)
-    print(f"  {results['int8_static_percentile_conv']['size_mb']:.3f} MB")
-    sess_int8 = ort_session(TINY_INT8_ONNX)
-    yq = sess_int8.run(None, {sess_int8.get_inputs()[0].name: fx})[0]
-    results["int8_static_percentile_conv"]["max_abs_diff_vs_fp32_fixture"] = float(
-        np.abs(yq - y_torch).max())
-
-    # ---- latency (3 interleaved reps, full-model sessions as references) -----
-    print("\n=== latency (3 interleaved reps) ===")
-    lat_sessions = {
-        "tiny_onnx_fp32": sess_fp32,
-        "tiny_onnx_int8_static_percentile_conv": sess_int8,
-        "full_onnx_fp32_reference": ort_session(FULL_FP32_ONNX),
-        "full_onnx_int8_static_percentile_conv_reference": ort_session(FULL_INT8_ONNX),
-    }
-    results["latency"] = {
-        "note": "3 interleaved repetitions per variant, median ms/window; "
-                "full-model sessions are same-session references",
-        **interleaved_latency(lat_sessions),
-    }
-
-    # ---- accuracy on the standard 10k corruption-free test subset ------------
-    if not args.skip_accuracy:
-        loader, n_clean = build_test_subset(args.data_dir, args.subset)
-        results["accuracy_subset"] = {
-            "description": "seed-42 file-level 70/15/15 test split, corrupted "
-                           "windows excluded, seed-42 random subset (same as "
-                           "quantize_bench/eval_ort_accuracy/static_ptq_bench)",
-            "subset_size": min(args.subset, n_clean) if args.subset else n_clean,
-        }
-        results["accuracy"] = {}
-        for name, sess in (("tiny_onnx_fp32", sess_fp32),
-                           ("tiny_onnx_int8_static_percentile_conv", sess_int8)):
-            print(f"\n=== accuracy: {name} ===")
-            results["accuracy"][name] = evaluate_ort(sess, loader, name)
-            print(json.dumps(results["accuracy"][name], indent=2))
-
-    # ---- merge into edge_optimization.json -----------------------------------
-    merged = {}
-    if os.path.exists(args.out):
-        with open(args.out) as f:
-            merged = json.load(f)
-    merged["tiny_variant"] = results
-    with open(args.out, "w") as f:
-        json.dump(merged, f, indent=2)
-    print(f"\nwrote {args.out}")
-
-
-if __name__ == "__main__":
-    main()
@@ -14,13 +14,6 @@ COPY v2/crates/ ./crates/
 # Copy vendored RuVector crates
 COPY vendor/ruvector/ /build/vendor/ruvector/

-# Copy vendored RuField submodule — the `wifi-densepose-rufield` bridge crate
-# (ADR-262) path-deps `../../../vendor/rufield/crates/*`, which from the Docker
-# build layout (v2/ collapsed into /build) resolves to /vendor/rufield. Copy the
-# whole tree so the rufield workspace Cargo.toml (workspace-dep inheritance) and
-# the four bridged crates (rufield-core/-provenance/-privacy/-fusion) all resolve.
-COPY vendor/rufield/ /vendor/rufield/
-
 # Build release binaries:
 #   - sensing-server with `mqtt` feature so the HA-DISCO MQTT publisher
 #     (ADR-115) is wired in (auto-discovery topics flow to Home Assistant)
@@ -24,13 +24,10 @@ services:
    environment:
      - RUST_LOG=info
      # CSI_SOURCE controls the data source for the sensing server.
-      # Options: auto (default) — probe for ESP32 UDP then host WiFi; **fail
-      #                           hard with exit 78 if neither is detected**.
-      #                           Synthetic data is no longer a silent fallback
-      #                           (issue #937 fix) — operators must opt in.
+      # Options: auto (default) — probe for ESP32 UDP then fall back to simulation
      #          esp32          — receive real CSI frames from an ESP32 on UDP port 5005
      #          wifi           — use host Wi-Fi RSSI/scan data (Windows netsh)
-      #          simulated      — explicitly generate synthetic CSI for demo mode
+      #          simulated      — generate synthetic CSI data (no hardware required)
      - CSI_SOURCE=${CSI_SOURCE:-auto}
      # MODELS_DIR controls where the server scans for .rvf model files.
      # Mount a host directory and set this to make models visible:
@@ -11,65 +11,10 @@
 #      docker run ruvnet/wifi-densepose:latest --model /app/models/my.rvf
 #
 # Environment variables:
-#   CSI_SOURCE   — data source. Valid values:
-#                    auto       — try ESP32 then Windows WiFi, **fail-loud if no
-#                                 real hardware is detected** (issue #937 fix:
-#                                 the server no longer silently falls back to
-#                                 synthetic data — that's now opt-in only).
-#                    esp32      — listen for UDP CSI on the configured port.
-#                    wifi       — Windows-native WiFi capture.
-#                    simulated  — explicit demo mode with synthetic CSI.
-#                  Default is `auto`. Set CSI_SOURCE=simulated when you want
-#                  fake data tagged as such; never set it implicitly.
+#   CSI_SOURCE   — data source: auto (default), esp32, wifi, simulated
 #   MODELS_DIR   — directory to scan for .rvf model files (default: data/models)
 set -e

-# ── Issue #864: fail-closed on default posture ───────────────────────────────
-# The pre-fix default was: empty RUVIEW_API_TOKEN (auth off) + --bind-addr
-# 0.0.0.0 + docker-compose publishing :3000/:3001/:5005 → an unauthenticated
-# attacker on any reachable network segment could read /api/v1/sensing/latest
-# and the /ws/sensing live stream. That posture is unsafe on guest WiFi,
-# untrusted LANs, accidentally-port-forwarded hosts, or any reverse-proxied
-# deployment. Refuse to start with this combination.
-#
-# Escape hatches (operator must opt in explicitly):
-#   * Set RUVIEW_API_TOKEN to a strong secret → auth enabled on /api/v1/*.
-#   * Set RUVIEW_ALLOW_UNAUTHENTICATED=1 → preserves the pre-fix behaviour;
-#     only safe on an isolated trust boundary.
-#   * Set RUVIEW_BIND_ADDR to a loopback / private interface → unauth is fine
-#     when the socket isn't reachable. The auto-bind nudges toward 127.0.0.1.
-#
-# This check runs only for the default sensing-server path (no args + flag-only
-# args). The `cog-ha-matter` / `homecore` routes below are excluded because
-# they own their own auth lifecycle.
-case "${1:-}" in
-    cog-ha-matter|ha-matter|homecore|homecore-server) ;;
-    *)
-        if [ -z "${RUVIEW_API_TOKEN:-}" ] && [ "${RUVIEW_ALLOW_UNAUTHENTICATED:-}" != "1" ]; then
-            # If the operator hasn't overridden the bind, refuse outright on
-            # the default 0.0.0.0. If they've nailed it to loopback (or a
-            # specific private address they trust), let it run.
-            __bind_default="${RUVIEW_BIND_ADDR:-0.0.0.0}"
-            case "$__bind_default" in
-                127.*|localhost|::1)
-                    : ;;  # loopback bind is safe even without a token
-                *)
-                    echo "[entrypoint] ERROR: refusing to start sensing-server with default" >&2
-                    echo "[entrypoint]        posture: RUVIEW_API_TOKEN is unset AND bind is" >&2
-                    echo "[entrypoint]        ${__bind_default}. /ws/sensing streams live sensing" >&2
-                    echo "[entrypoint]        frames; that data would be readable by anyone who" >&2
-                    echo "[entrypoint]        can reach this host. Pick one:" >&2
-                    echo "[entrypoint]          docker run -e RUVIEW_API_TOKEN=\$(openssl rand -hex 32) ..." >&2
-                    echo "[entrypoint]          docker run -e RUVIEW_BIND_ADDR=127.0.0.1 ..." >&2
-                    echo "[entrypoint]          docker run -e RUVIEW_ALLOW_UNAUTHENTICATED=1 ...   # only on trusted network" >&2
-                    echo "[entrypoint]        See https://github.com/ruvnet/RuView/issues/864" >&2
-                    exit 64
-                    ;;
-            esac
-        fi
-        ;;
-esac
-
 # Route to cog-ha-matter (ADR-116) when invoked as:
 #   docker run <image> cog-ha-matter [--flags]
 # or via the short alias `ha-matter`. Strips the keyword and execs the
@@ -103,7 +48,7 @@ if [ "${1#-}" != "$1" ] || [ -z "$1" ]; then
        --ui-path /app/ui \
        --http-port 3000 \
        --ws-port 3001 \
-        --bind-addr "${RUVIEW_BIND_ADDR:-0.0.0.0}" \
+        --bind-addr 0.0.0.0 \
        "$@"
 fi

@@ -57,7 +57,7 @@ This witness separates what was **empirically observed on real silicon today** f

 | # | Claim | Why it's not verified |
 |---|---|---|
-| **B1** | "Wi-Fi 6 HE-LTF: 242 subcarriers per HE20 frame" | The only AP in range (`ruv.net`) is 11n-only. Every captured frame is 128 bytes = 64 subcarriers (HT-LTF, `ppdu_type=0`). No HE-SU/HE-MU/HE-TB observed. Even if an 11ax AP were available, **whether ESP-IDF v5.4's CSI callback exposes HE-LTF subcarriers via `wifi_csi_info_t.buf` is an open question** — the public API was designed for HT-LTF, and the driver may quietly downconvert. **Validate by capturing CSI against an 11ax AP and comparing `info->len` between HT and HE frames.**<br><br>**RESOLVED WITH MEASUREMENT (2026-06-11, external — issue #1005, production deployment by @stuinfla):** the open question is answered in both directions. **IDF v5.4's driver blob downconverts** (148 B / 64-subcarrier HT frames, PPDU byte 0x00, on a confirmed-HE link); **IDF v5.5.2 delivers true HE-LTF** — 532 B frames = 256 bins (242 active HE20 tones), PPDU byte 0x01 (HE-SU), ~90% of frames, same board/AP/link. Setup: XIAO ESP32-C6 → hostapd on Intel AX210, 2.4 GHz ch 6, `ieee80211ax=1`. No firmware change required (`acquire_csi_su=1` was already set); the gate was purely the IDF driver version. Three C6 nodes ran this mode simultaneously with ADR-110 ESP-NOW sync. Requires the issue-#1005 version-guard fix in `c6_sync_espnow.c` to build on v5.5.x. |<br><br>**REPLICATED IN-HOUSE (2026-06-11):** same source + fix, fresh IDF v5.5.2 toolchain, original COM12 board (`20:6e:f1:17:00:84`), AP `ruv.net` (11ax 2.4 GHz): **84% of 1,525 captured frames at 532 B / PPDU 0x01 (HE-SU)**, HT minority 148 B / 0x00. Evidence grade: MEASURED (two independent rigs). |
+| **B1** | "Wi-Fi 6 HE-LTF: 242 subcarriers per HE20 frame" | The only AP in range (`ruv.net`) is 11n-only. Every captured frame is 128 bytes = 64 subcarriers (HT-LTF, `ppdu_type=0`). No HE-SU/HE-MU/HE-TB observed. Even if an 11ax AP were available, **whether ESP-IDF v5.4's CSI callback exposes HE-LTF subcarriers via `wifi_csi_info_t.buf` is an open question** — the public API was designed for HT-LTF, and the driver may quietly downconvert. **Validate by capturing CSI against an 11ax AP and comparing `info->len` between HT and HE frames.** |
 | **B2** | "TWT-bounded deterministic CSI cadence (10 ms wake)" | No 11ax AP in range. The TWT setup *call* was exercised live and the graceful fallback path is now correct (A9), but the agreement itself was never accepted. **Validate by associating with an 11ax AP that has TWT Responder=1, then capturing the timestamped CSI cadence vs the wall clock.** |
 | **B3** | "±100 µs cross-node alignment over 802.15.4" | 3 boards initialized their radios with correct EUIs (A4/A5), but **none stepped down from candidate-leader to follower** during repeated 35-second multi-board captures. <br><br>**Coex hypothesis REJECTED**: rebuilt + reflashed all 3 boards with `CONFIG_C6_TIMESYNC_CHANNEL=26` (2480 MHz, non-overlapping with WiFi ch 5 at 2432 MHz). Result identical: 3× candidate, 0× "stepping down". So 2.4 GHz radio coex was NOT the cause. <br><br>**Current leading hypothesis**: OpenThread (CONFIG_OPENTHREAD_ENABLED=y) owns the 802.15.4 radio when its stack is initialized — our weak-symbol overrides of `esp_ieee802154_receive_done` / `_transmit_done` may never be called because OpenThread registers strong handlers. Validation in progress: rebuilding with `CONFIG_OPENTHREAD_ENABLED=n` (raw 802.15.4 only, our beacon protocol is private — no need for the Thread stack). If leader election fires under raw-15.4-only, hypothesis confirmed. <br><br>If raw-only also fails, next move is to dump the actual PHY frame bytes via the IEEE 802.15.4 sniffer mode on a 4th board and diagnose at the frame level. |
 | **B4** | "~5 µA hibernation for battery seed nodes" | No INA / Joulescope current measurement available on this bench. The shipped code uses `esp_deep_sleep_enable_gpio_wakeup` (ext1 path, ESP-IDF default ~10 µA), not a true LP-core polling program. The 5 µA number is the C6 datasheet figure for ULP-level hibernation, not a measured value. **Validate by hooking an INA219/INA226 between the dev board's 3V3 rail and the regulator output, then averaging current over a 60-second cycle with the LP-core armed.** |
@@ -1081,23 +1081,6 @@ The `wifi-densepose-vitals` crate (ESP32 CSI-grade vital signs) has not yet been
 - SONA-based environment adaptation
 - VitalSignStore with tiered temporal compression

-## Implementation Notes
-
-### 2026-06 — ESP32 edge vitals: person-count over-count + presence flicker (#998, #996)
-
-Two robustness bugs were fixed in the on-device edge path (`firmware/esp32-csi-node/main/edge_processing.c`, the ADR-039 packet `0xC5110002`). These touch the *boolean/count emission logic*, not the underlying CSI signal-processing math, and do **not** constitute a validated-accuracy claim — true occupancy-count and presence accuracy vs labelled ground truth remain hardware/data-gated (COM9 ESP32-S3 + labelled capture).
-
- **#998 `n_persons` over-count (reported 4 for one person).** `update_multi_person_vitals()` divided the top-K subcarriers into `top_k_count/2` groups and marked *every* group `active`, so one body's multipath always read the full `EDGE_MAX_PERSONS`. Added an energy gate (`EDGE_PERSON_MIN_ENERGY_RATIO`), spatial dedup (`EDGE_PERSON_MIN_SC_SEP`), and a persistence debounce (`EDGE_PERSON_PERSIST_FRAMES`) via two pure functions `count_distinct_persons()` / `person_count_debounce()`.
- **#996 presence flag flicker at ~50 cm.** Single-threshold compare on a noisy `presence_score` chattered at the boundary. Replaced with a Schmitt trigger + clear-debounce (`presence_flag_update()`, constants `EDGE_PRESENCE_HYST_RATIO` / `EDGE_PRESENCE_CLEAR_FRAMES`); `presence_score` is unchanged and still emitted for consumer-side thresholding.
-
-Both are pinned by host-buildable C99 tests in `firmware/esp32-csi-node/test/test_vitals_count_presence.c` (`make run_vitals`). The exact thresholds are documented constants pending on-device calibration against ground truth.
-
-### 2026-06 — Rust `wifi-densepose-vitals`: IIR filter NaN/inf self-heal (ADR-158 §A1)
-
-A correctness/safety review of the Rust extraction crate found a real bug parallel to the firmware robustness class above. The 2nd-order resonator `bandpass_filter` in both `breathing.rs` and `heartrate.rs` latches each output `y[n]` into its filter state (`y1`/`y2`). A single non-finite amplitude residual from a corrupt CSI frame produced a NaN `output` that was written into the state; the existing `extract()` `is_finite()` guard dropped that one sample from the history buffer **but never sanitized the poisoned filter state**, so every later output stayed NaN, was rejected too, and the sliding-window history never refilled — breathing **and** heart-rate extraction went silently dead (returning `None` forever) until `reset()`. On the alert path this is a safety-relevant denial of service (one bad frame stops vitals monitoring with no error surfaced).
-
-Fix: when `bandpass_filter` computes a non-finite `output`, it resets the IIR state to default and returns `0.0`, so the resonator self-heals on the next clean frame (the `0.0` is still dropped by the caller's finite-check, so no spurious sample enters history). Same shape as the calibration NaN bug (ADR-154 §3) — the prior hardening guarded the *history boundary* but not the *filter-state boundary*. Pinned by `breathing::tests::nan_frame_does_not_permanently_poison_filter`, `breathing::tests::inf_mid_stream_does_not_freeze_history`, and `heartrate::tests::nan_frame_does_not_permanently_poison_filter` (all FAIL pre-fix, verified by reverting). The review also de-magicked the HR physiological plausibility band into named `HR_PLAUSIBLE_MIN_BPM`/`HR_PLAUSIBLE_MAX_BPM` consts (value-identical 40/180 BPM) and added a fabricated-vital negative (`pure_noise_is_never_reported_valid` — broadband noise never yields a clinically `Valid` HR; the extractor honestly returns low-confidence `Unreliable`). Clean dimensions confirmed with evidence: flat/silent input → `None`; pure noise → low-confidence `Unreliable`, never `Valid`; harmonic-rich breathing with no cardiac component → low-confidence, not a confident false HR; out-of-band BPM rejected by the plausibility clamp.
-
 ## References

 - Ramsauer et al. (2020). "Hopfield Networks is All You Need." ICLR 2021. (ModernHopfield formulation)
@@ -1,4 +1,4 @@
-# ADR-166: Quality Engineering Response — Security Hardening & Code Quality
+# ADR-050: Quality Engineering Response — Security Hardening & Code Quality

 | Field | Value |
 |-------|-------|
@@ -1,8 +1,4 @@
-# ADR-167 Appendix: DDD Bounded Contexts — Tauri Desktop Frontend
-
-> Appendix to [ADR-052](ADR-052-tauri-desktop-frontend.md). Renumbered from ADR-052
-> to ADR-167 to resolve the ADR-052 duplicate-number collision (per ADR-164 Gap Register
-> G1); the parent decision remains ADR-052.
+# ADR-052 Appendix: DDD Bounded Contexts — Tauri Desktop Frontend

 This document maps out the domain model for the RuView Tauri desktop application
 described in ADR-052. It defines bounded contexts, their aggregates, entities,
@@ -162,7 +158,7 @@ Represents an over-the-air firmware update to a running node.
 | `target_node` | `MacAddress` | Target node MAC |
 | `target_ip` | `IpAddr` | Target node IP |
 | `firmware` | `FirmwareBinary` | The binary being pushed |
-| `psk` | `Option<SecureString>` | PSK for authentication (ADR-166) |
+| `psk` | `Option<SecureString>` | PSK for authentication (ADR-050) |
 | `phase` | `OtaPhase` | Uploading / Rebooting / Verifying / Done / Failed |
 | `progress` | `Progress` | Upload progress |

@@ -5,7 +5,7 @@
 | Status | Proposed |
 | Date | 2026-03-06 |
 | Deciders | ruv |
-| Depends on | ADR-012 (ESP32 CSI Mesh), ADR-039 (Edge Intelligence), ADR-040 (WASM Programmable Sensing), ADR-044 (Provisioning Enhancements), ADR-166 (Security Hardening, renumbered from ADR-050), ADR-051 (Server Decomposition) |
+| Depends on | ADR-012 (ESP32 CSI Mesh), ADR-039 (Edge Intelligence), ADR-040 (WASM Programmable Sensing), ADR-044 (Provisioning Enhancements), ADR-050 (Security Hardening), ADR-051 (Server Decomposition) |
 | Issue | [#177](https://github.com/ruvnet/RuView/issues/177) |

 ## Context
@@ -211,7 +211,7 @@ pub struct FlashProgress {
 // commands/ota.rs

 /// Push firmware to a node via HTTP OTA (port 8032).
-/// Includes PSK authentication per ADR-166.
+/// Includes PSK authentication per ADR-050.
 #[tauri::command]
 async fn ota_update(
    node_ip: String,
@@ -801,7 +801,7 @@ Total estimated effort: ~11 weeks for a single developer.
 - ADR-039: ESP32 Edge Intelligence
 - ADR-040: WASM Programmable Sensing
 - ADR-044: Provisioning Tool Enhancements
- ADR-166: Quality Engineering — Security Hardening (renumbered from ADR-050)
+- ADR-050: Quality Engineering — Security Hardening
 - ADR-051: Sensing Server Decomposition
 - `firmware/esp32-csi-node/` — ESP32 firmware source
 - `firmware/esp32-csi-node/provision.py` — Current provisioning script
@@ -1,6 +1,6 @@
 # ADR-080: QE Analysis Remediation Plan

- **Status:** Proposed — P0 security findings #1–#3 **RESOLVED** on the shipped Rust sensing-server boundary (2026-06-13; closes ADR-164 G11)
+- **Status:** Proposed
 - **Date:** 2026-04-06
 - **Source:** [QE Analysis Gist (2026-04-05)](https://gist.github.com/proffesor-for-testing/a6b84d7a4e26b7bbef0cf12f932925b7)
 - **Full Reports:** [proffesor-for-testing/RuView `qe-reports` branch](https://github.com/proffesor-for-testing/RuView/tree/qe-reports/docs/qe-reports)
@@ -13,38 +13,25 @@ An 8-agent QE swarm analyzed ~305K lines across Rust, Python, C firmware, and Ty

 Address the 15 prioritized issues from the QE analysis in three waves: P0 (immediate), P1 (this sprint), P2 (this quarter).

-## Security P0 closure note (2026-06-13) — Rust sensing-server boundary
-
-The three P0 security findings below were logged against the **Python v1** API
-(`archive/v1/src/…`). ADR-164 G11 re-scoped them to the *shipped* boundary:
-`wifi-densepose-sensing-server` (Rust). They were verified against the current
-Rust crate and closed on branch `fix/adr-080-sensing-server-security`. Each fix
-(or already-fixed finding) is pinned by a test that fails on the old behavior.
-**The Python v1 paths remain as-is** — v1 is archived and not the shipped
-surface; this closure governs the live Rust server only.
-
 ## P0 — Fix Immediately

-### 1. Rate Limiter Bypass / XFF spoofing (Security HIGH) — **RESOLVED (verified absent on Rust boundary)**
+### 1. Rate Limiter Bypass (Security HIGH)

- **Original location (v1):** `archive/v1/src/middleware/rate_limit.py:200-206`
+- **Location:** `archive/v1/src/middleware/rate_limit.py:200-206`
 - **Problem:** Trusts `X-Forwarded-For` without validation. Any client bypasses rate limits via header spoofing.
- **Rust verification (2026-06-13):** The Rust sensing-server has **no XFF-trusting control to bypass** — there is no IP-based rate-limiter and no IP-allowlist, and neither security middleware reads a forwarded header. `bearer_auth.rs` authenticates on the token alone (`require_bearer` inspects only the `AUTHORIZATION` header); `host_validation.rs` decides on the `Host` header only. A repo-wide grep for `x-forwarded-for|forwarded|peer_addr|client_ip|real-ip` over `wifi-densepose-sensing-server` returns nothing. The only "rate limiter" is the MQTT *sample-rate* gate (`mqtt/state.rs`), a per-entity publish throttle with no IP/header input.
- **Resolution:** No code change needed (no vulnerable surface). Regression tests pin the immunity: `bearer_auth::tests::xff_header_never_affects_auth_decision` (spoofed XFF never flips a 401↔200 decision) and `host_validation::tests::forwarded_headers_never_bypass_host_allowlist` (spoofed `X-Forwarded-Host: localhost` never lets a foreign `Host: evil.com` past the allowlist). Residual: if an IP-based control is ever added, it must derive the peer from the socket (`ConnectInfo<SocketAddr>`) and only honor XFF from an explicit `--trusted-proxy` CIDR — captured as guidance in the test docstrings.
+- **Fix:** Validate forwarded headers against trusted proxy list, or use connection IP directly.

-### 2. Exception Details Leaked in Responses (Security HIGH, CWE-209) — **RESOLVED**
+### 2. Exception Details Leaked in Responses (Security HIGH)

- **Original location (v1):** `archive/v1/src/api/routers/pose.py:140`, `stream.py:297`, +5 endpoints
- **Problem:** Internal error/stack-trace detail serialized into client responses.
- **Rust finding (2026-06-13):** Six handlers in `wifi-densepose-sensing-server/src/main.rs` serialized the internal error `Display` into the JSON body: `edge_registry_endpoint` returned a panicked `spawn_blocking` `JoinError` (`"task … panicked"`) in a `500` and the raw upstream error in a `503`; `delete_model`/`delete_recording`/`start_recording` returned `std::io::Error` strings (OS detail / path); `calibration_start`/`calibration_stop` returned the `FieldModel` error chain.
- **Fix:** New `src/error_response.rs` module — `internal_error` / `internal_error_json` / `upstream_unavailable` log the full detail **server-side only** (tagged with a correlation id) and return a generic body (`{"error":"internal_error","correlation_id":…}`) with no `panicked`, no file paths, no Debug chain. All six call-sites rewired. Pinned by `error_response::tests::internal_error_body_does_not_leak_detail` (leak-substring guard, verified to fail on the reverted old body) + 4 sibling tests.
+- **Location:** `archive/v1/src/api/routers/pose.py:140`, `stream.py:297`, +5 endpoints
+- **Problem:** Stack traces visible regardless of environment.
+- **Fix:** Wrap with generic error responses in production; log details server-side only.

-### 3. WebSocket JWT in URL (Security HIGH, CWE-598) — **RESOLVED (verified absent on Rust boundary)**
+### 3. WebSocket JWT in URL (Security HIGH, CWE-598)

- **Original location (v1):** `archive/v1/src/api/routers/stream.py:74`, `archive/v1/src/middleware/auth.py:243`
+- **Location:** `archive/v1/src/api/routers/stream.py:74`, `archive/v1/src/middleware/auth.py:243`
 - **Problem:** Tokens in query strings visible in logs/proxies/browser history.
- **Rust verification (2026-06-13):** The Rust sensing-server never reads a token from the URL. `require_bearer` (`bearer_auth.rs`) inspects only the `Authorization` header; the WebSocket handlers (`ws_sensing_handler`/`ws_introspection_handler`/`ws_pose_handler`) take a bare `WebSocketUpgrade` with no `Query` extractor; the single `Query` in the crate (`EdgeRegistryParams`) is a non-secret `refresh` flag.
- **Resolution:** No code change needed (no query-token path exists). Regression test `bearer_auth::tests::query_string_token_is_never_accepted` proves `?token=`/`?access_token=` in the URL never authenticates (stays `401`) while the same token in the header succeeds (`200`) — verified to fail if a query-token path is re-introduced.
+- **Fix:** Use WebSocket subprotocol or first-message auth pattern.

 ### 4. Rust Tests Not in CI

@@ -259,75 +259,14 @@ Validation runs against:
 - **ADR-083** (Proposed) — Per-cluster Pi compute hop. Defines the
  device class that hosts the sketch bank.

-## Pass 2 — randomized rotation + multi-bit (ADR-156 §8, landed 2026-06)
-
-The "Open question" below ("does `BinaryQuantized` need a randomized
-rotation pre-pass?") is now **answered with measured numbers** via
-ADR-156 §10. Summary:
-
- **Pass 2 (randomized rotation) is implemented** —
-  `crates/wifi-densepose-ruvector/src/rotation.rs`: a deterministic
-  `R = H·D` (Fast Hadamard Transform + seeded ±1 sign flips), `O(d log d)`
-  / `O(d)`, norm-preserving, reproducible from a stored `u64` seed. Opt-in
-  via `Sketch::from_embedding_rotated` / `SketchBank::with_rotation`;
-  Pass-1 API and wire format unchanged.
- **Measured top-K coverage** (anisotropic planted-cluster fixture,
-  cosine ground truth, dim=128 N=2048 K=8): rotation lifts coverage
-  **36.13% → 46.39%** at the strict `candidate_k = K` bar, and Pass-2
-  reaches the **≥90% acceptance bar at candidate_k = 24 (~3× over-fetch)**.
-  Multi-bit (≤4-bit) reaches 74% at the strict bar. **Honest verdict:
-  neither rotation nor ≤4-bit multi-bit clears the strict-K 90% bar on
-  this distribution; the bar is met via the over-fetch "candidate set"
-  pattern this ADR specifies** (Decision §"the canonical pattern" — sketch
-  picks the candidate set, full precision refines). Full numbers and
-  reproduce commands in ADR-156 §10.
- **Pre-existing `SketchBank::topk` bug fixed** — the `n > k` heap path
-  returned the k *farthest* sketches (min-heap mistaken for max-heap);
-  only the `n ≤ k` fast path had test coverage. Fixed + regression-pinned
-  (`topk_heap_path_returns_nearest`,
-  `tight_clusters_give_high_coverage_with_overfetch`). This makes every
-  prior top-K acceptance number in this ADR depend on the fixed path; the
-  ≥90% coverage criterion is only meaningful post-fix.
-
-## Pass 2b — RaBitQ unbiased distance estimator (ADR-156 §11, landed 2026-06)
-
-The **real** RaBitQ contribution (Gao & Long, SIGMOD 2024) — an
-**unbiased estimator of the inner product / distance** from the 1-bit
-code + per-vector side info, not just sign bits — is now implemented and
-**MEASURED against this ADR's ≥90% strict-K bar**:
-
- **Implemented** — `crates/wifi-densepose-ruvector/src/estimator.rs`:
-  `EstimatorSketch` (Pass-2 sign code + 8 B/vec side info:
-  `residual_norm` + `x_dot_o = ⟨x̄, o'⟩`), `DistanceEstimator`
-  (`⟨o',q'⟩ ≈ ⟨x̄,q'⟩ / x_dot_o`, the paper's unbiased rescale), and
-  `EstimatorBank` reranking candidates by the estimate instead of raw
-  Hamming. **Zero-centroid simplification** (`c = 0`) documented;
-  paper-faithful centroid path also built (`with_centroid`). Additive —
-  Pass-1/Pass-2 and the wire format are unchanged.
- **MEASURED strict-K coverage** (same fixture as §"Pass 2", cosine
-  ground truth): the estimator lifts the strict `candidate_k = K` bar
-  **46.39% (Pass-2 sign) → 49.71% (estimator, cosine rerank)** — a real
-  **+3.3 pp** lift, but **still ~40 pp short of the ≥90% strict bar.**
-  At over-fetch the estimator does better than sign (95.12% vs 91.60% at
-  candidate_k = 24). **Honest verdict: the unbiased estimator does NOT
-  clear the strict-K 90% bar on this distribution** — the binding
-  constraint is the 1-bit code's information ceiling, not estimator
-  variance. The ≥90% acceptance bar is still met only via the over-fetch
-  "candidate set" pattern this ADR's Decision specifies; the estimator
-  **reduces the over-fetch factor** needed but does not remove it. This
-  is a **published negative**, reported as such. Full numbers + reproduce
-  commands in ADR-156 §11.
-
 ## Open questions

 - **Does `BinaryQuantized` need a randomized rotation pre-pass for
-  RuView's embedding distributions?** **ANSWERED (ADR-156 §10):** rotation
-  is built and measured — it helps (+10pp at strict K) but is not
-  sufficient alone for strict-K 90% on the tested anisotropic
-  distribution; the over-fetch candidate-set pattern meets the bar.
-  Pure sign quantization assumes zero-centered, isotropic embeddings; the
-  rotation decorrelates anisotropic coords as the RaBitQ paper
-  (Gao & Long, SIGMOD 2024) prescribes.
+  RuView's embedding distributions?** Pure sign quantization assumes
+  zero-centered, isotropic embeddings. If AETHER / spectrogram
+  distributions are skewed (likely for spectrogram), add a
+  `randomized_rotation` pre-pass following the original RaBitQ paper
+  (Gao & Long, SIGMOD 2024). Decided after pass-1 benchmark.
 - **Sketch dimension target.** Default to the embedding's native
  dimension (128 for AETHER, 256 for spectrogram). Higher-dimensional
  sketches (Johnson-Lindenstrauss-projected to 512) trade compute for
@@ -19,7 +19,7 @@ The production CSI node firmware (`firmware/esp32-csi-node`) was built around th

 | C6 capability | What it enables for sensing | Why we can't get it on S3 |
 |---|---|---|
-| **802.11ax (Wi-Fi 6) HE-LTF CSI** | 242 subcarriers per HE20 frame (vs 52 for HT-LTF), HE-MU/HE-TB PPDU types, OFDMA-aware channel sounding. **Hardware-confirmed 2026-06-11** (issue #1005, external production deployment): requires **ESP-IDF ≥ 5.5** — the v5.4 driver blob silently downconverts to 64-subcarrier HT even on a confirmed-HE link; v5.5.2 delivers 532 B frames = 256 bins (242 active tones), PPDU 0x01 (HE-SU). See WITNESS-LOG-110 §B1 (resolved). | S3 radio is HT-only (n) |
+| **802.11ax (Wi-Fi 6) HE-LTF CSI** | 242 subcarriers per HE20 frame (vs 52 for HT-LTF), HE-MU/HE-TB PPDU types, OFDMA-aware channel sounding | S3 radio is HT-only (n) |
 | **802.15.4 (Thread / Zigbee)** | Cross-node time-sync over a separate radio — frees Wi-Fi airtime for CSI, ±100 µs alignment possible without coordination traffic on the sensing channel | S3 has no 802.15.4 |
 | **TWT (Target Wake Time)** | Sensor negotiates a deterministic wake slot with the AP; CSI cadence becomes scheduler-bounded instead of opportunistic | Requires 802.11ax — S3 can't speak it |
 | **LP-core + hibernation (~5 µA)** | Always-on motion gate runs on a separate RISC-V LP core in deep sleep; HP core stays off until a real event | S3 ULP is FSM-only, ~10 µA floor |
@@ -104,57 +104,6 @@ Ranked by build cost × user impact:
 | **P9** | HACS integration repo (`hass-wifi-densepose`) for HA-side install path | pending |
 | **P10** | Witness bundle + CSA-style spec compliance check | pending |

-## 4.1 Crypto/security review notes (§2.2 witness chain — ADR-262 P2 prerequisite)
-
-Beyond-SOTA crypto+security review of the SHA-256 + Ed25519 witness chain
-(`witness.rs` / `witness_signing.rs`) and the manifest signature surface
-(`manifest.rs`), because ADR-262 P2 proposes to **reuse this exact signing
-chain**. Top priority was the sibling `wifi-densepose-engine` bug class —
-unframed boundary-to-boundary concatenation of operator-influenceable strings
-into a signed/hashed digest.
-
- **Engine bug class ABSENT (good result, reported with byte evidence).**
-  `canonical_bytes` is `DOMAIN_TAG ‖ prev_hash[32] ‖ seq:u64-be ‖ ts:u64-be ‖
-  kind_len:u32-be ‖ kind ‖ payload_len:u32-be ‖ payload`. The two
-  variable-length operator-influenceable fields (`kind`, `payload`) are
-  **length-prefixed**; the fixed-width fields are self-delimiting → the
-  encoding is injective (no two distinct event tuples share a preimage). The
-  Ed25519 signature signs the **identical** bytes the SHA-256 chain commits to.
-  No separate unframed concatenation exists; the manifest `binary_signature`
-  is signed at build time (Makefile) over a single fixed-length `binary_sha256`
-  hex value, not in-crate.
-
- **CHM-WIT-01 (FIXED) — domain-separation tag added.** The engine fix
-  prescribed *domain-tag + length-prefix*; length-prefix was present, the
-  domain tag was not. Added a versioned, NUL-terminated
-  `WITNESS_DOMAIN_TAG = b"cog-ha-matter/witness-event/v1\x00"` prefix so the
-  witness message can never be replayed as a message for another Ed25519
-  context that shares key infrastructure (notably the manifest signature).
-  **Witness bytes change by design** (prior on-disk hashes/signatures
-  invalidated, as with the engine fix); verified safe because no in-repo crate
-  consumes cog-ha-matter witness bytes programmatically (doc-mentions only).
-
- **CHM-WIT-02 (HARDENED) — `verify_signature` now uses `verify_strict`.** For
-  an audit chain the signature is the attestation, so non-canonical encodings
-  and small-order keys are rejected (RFC 8032 strict), giving the "one
-  canonical signature per event" property. Not a forgery fix — the verifying
-  key is caller-pinned, never read from the event.
-
- **Confirmed clean (with evidence):** verify-before-trust + key-pinning
-  (`verify_signature` takes the verifying key as a parameter; `read_jsonl`
-  re-derives every hash and chain-verifies); key handling (the crate never
-  generates/stores/logs/serializes a signing key — only a documented test-only
-  fixed seed; production keys come from the Seed secure store, out of scope);
-  determinism (positional bytes, deterministic Ed25519, alphabetically-locked
-  JSONL field order, sorted TXT records — no HashMap/float nondeterminism feeds
-  any digest); fail-closed parsing (structured errors, no panics; `main.rs`
-  reads no untrusted files/paths).
-
-Tests: `cog-ha-matter --no-default-features` 64 → **68**, 0 failed (CHM-WIT-01
-pinned by 4 fails-on-old tests across `witness.rs`/`witness_signing.rs`;
-CHM-WIT-02 guarded by a key-pinning test). Python deterministic proof
-unchanged (cog-ha-matter is off the signal proof path).
-
 ## 5. References

 - ADR-101 — `cog-pose-estimation` packaging precedent (signed binaries on GCS, .cog manifest)
@@ -190,78 +190,4 @@ The entity registry is a `RwLock<HashMap<EntityId, EntityEntry>>` backed by an a

 - `v2/crates/wifi-densepose-sensing-server/src/main.rs` — Axum + Tokio architecture pattern used throughout the existing server stack
 - `docs/adr/ADR-126-ruview-native-ha-port-master.md` — HOMECORE master; §5.5 crate naming; §6 compatibility contract; §5.1 RUVIEW-POLICY
-
---
-
-## 9. Security & concurrency review (P1 core, beyond-SOTA sweep)
-
-Foundational review of the `homecore` crate — the state store + event bus +
-service/entity registries every other HOMECORE module trusts. Same rigor as
-the ADR-129/130/132/133/161 sibling reviews. **Three real fixes (one
-concurrency, two hardening), each pinned by a fails-on-old test; the bus-lag
-and lock-discipline dimensions confirmed clean with evidence.**
-
- **HC-RACE-01 (state-set TOCTOU — lost / reordered `state_changed`, the
-  crux). FIXED.** `StateMachine::set` did `get()` (releasing the DashMap
-  shard lock) → compute the next snapshot + the no-op / `last_changed`
-  decision → `insert()` (re-acquiring the lock) → `send()`. The
-  read-modify-write was **not atomic** w.r.t. a concurrent writer on the
-  same entity, contradicting §2.1's promise that "the writer atomically
-  replaces the map entry." A writer that read a stale `old` could
-  mis-classify a genuine transition as a no-op and **drop its
-  `state_changed` event** (a missed automation trigger) or fire an event
-  whose `new_state` duplicated the previously delivered one (a spurious
-  trigger for any automation keyed on `old_state != new_state`). **Fix:**
-  hold the shard write-lock across the entire read→decide→insert→fire
-  sequence via `entry()`/`insert_entry()`; `tx.send` is non-blocking,
-  non-async, and never re-enters the map, so firing under the shard lock
-  cannot deadlock and keeps global event order in lock-step with global
-  commit order. Pinned by `concurrent_set_fires_no_duplicate_adjacent_events`
-  (4 writers toggling one entity A/B; asserts no two consecutive fired
-  events carry an identical `new_state` — impossible under correct
-  serialisation; a probe observed ~93k such duplicate-adjacent events across
-  200 trials on the racy code, zero on the fix).
- **HC-EID-LEN-01 (unbounded `entity_id` — memory-DoS at the REST boundary).
-  FIXED.** `homecore-api/src/rest.rs` parses untrusted path segments
-  straight through `EntityId::parse`; with no length cap, an
-  otherwise-valid id (`a.` + many MB of `[a-z0-9_]`) was accepted and a
-  `POST /api/states/<giant>` would persist it into the DashMap state store
-  (permanent growth across distinct ids). **Fix:** reject ids longer than
-  `MAX_ENTITY_ID_LEN` (255, HA-compatible) up front in `parse()`, before any
-  per-char scan, with a new `EntityIdError::TooLong`; fail-closed at the
-  boundary type protects every caller. Pinned by `entity_id_length_boundary`
-  (exactly-MAX accepted, MAX+1 and a 4 MiB id rejected — fails on old code).
- **HC-SVC-PANIC-01 (service-handler panic not isolated). HARDENED.**
-  `ServiceRegistry::call` already ran handlers outside the registry lock (no
-  `RwLock` poisoning, no blocking of other callers — clean), but a
-  panicking handler unwound through `call()` into the caller's task. **Fix:**
-  wrap the handler future in `AssertUnwindSafe` + `catch_unwind`, converting
-  a panic to `ServiceError::HandlerPanicked`; the registry stays fully
-  usable. Pinned by `panicking_handler_is_isolated_and_registry_survives`.
-
-**Dimensions confirmed clean (with evidence):**
-
- **Event-bus bounds / lag (same class as the homecore-api WS lag-DoS).**
-  Both `StateMachine` and `EventBus` use bounded `tokio::sync::broadcast`
-  (capacity 4,096). A slow subscriber gets a recoverable `Lagged(n)`
-  (drop-oldest + re-sync); `fire_*` is non-blocking and **never waits on
-  slow receivers**, so a lagging subscriber cannot block the publisher, grow
-  the channel without bound, or take down a fast subscriber. Evidenced by
-  `slow_subscriber_does_not_block_publisher_or_kill_the_bus` (fire 3×
-  capacity at an idle subscriber; publisher unblocked, bus stays live).
- **Lock ordering / lock-across-await (deadlock).** No code path holds two
-  of `{state DashMap, registry RwLock, service RwLock}` simultaneously, so
-  no inconsistent-ordering deadlock can exist. Every `tokio::sync::RwLock`
-  guard in `registry.rs`/`service.rs` is used in a single synchronous
-  statement and dropped before any `.await`; `call` explicitly scopes the
-  read guard out before awaiting the handler. The only guard held across a
-  send is the DashMap shard lock in `set`, across a synchronous
-  (non-await) broadcast send — safe.
- **Panic-on-input.** No reachable `unwrap`/`expect`/index in non-test code
-  beyond the safe `send().unwrap_or(0)` and the dead-but-harmless
-  `split_once(...).unwrap_or(...)` fallbacks on already-validated ids.
-
-`cargo test -p homecore --no-default-features`: **20 → 24 passed, 0 failed**
-(+4 pins). Workspace green; Python deterministic proof unchanged
-(`f8e76f21…46f7a`, bit-exact — `homecore` is off the signal proof path).
 - `docs/adr/ADR-028-esp32-capability-audit.md` — witness chain pattern (Ed25519 per state transition)
@@ -190,23 +190,6 @@ This is the same Wasmtime host already used for integration plugins (ADR-128)

 ---

-## 8a. Security review (beyond-SOTA sweep, post ADR-154–159)
-
-A focused security review of `homecore-automation` (the execution/eval surface — triggers → conditions → actions, with templates) was run after the ADR-154–159 sweep, applying the same rigor that the sibling engine/bfld/calibration/vitals/geo reviews used. **Two real DoS findings, each pinned by a fails-on-old test; the condition-bypass, fail-closed-parsing, and action-authorization dimensions were probed and found clean.**
-
- **HC-SEC-01 (template-injection / unbounded-expansion DoS, HIGH) — FIXED.** A `template:` condition / `value_template` is user automation config, and was rendered with MiniJinja's defaults: **no instruction budget, no output cap**. A single condition such as `{% for i in range(5000) %}{% for j in range(5000) %}xxxx{% endfor %}{% endfor %}` rendered a **100 MB string over ~11 s on one render call** (measured) — a CPU/memory denial of service (the bfld-class "unbounded expansion"; MiniJinja's per-call `range()` 10k cap does **not** stop nested loops). **Fix:** enable MiniJinja's `fuel` feature and set a per-render budget (`set_fuel(Some(1_000_000))`) so a nested loop burns one unit per iteration — the attack now fails fast (~90 ms) with "engine ran out of fuel"; plus a 64 KiB source-length cap rejecting pathological sources before compilation. Legitimate HA templates (a few dozen instructions) are unaffected. Pinned by `nested_loop_template_is_bounded_not_unbounded_dos`, `single_huge_repeat_template_is_bounded`, `oversized_template_source_is_rejected` (all fail-on-old: unbounded render / no rejection), and `legitimate_template_still_renders_within_fuel` (no regression).
- **HC-SEC-02 (panic-on-config DoS, MEDIUM) — FIXED.** `Action::Delay { seconds }` and `Action::WaitForTrigger { timeout_seconds }` fed the user-supplied float straight into `Duration::from_secs_f64`, which **panics** on negative, NaN, infinite, or overflowing inputs — all reachable from a crafted (or typo'd) YAML (`delay: {seconds: -1}`, `.nan`, `.inf`, `1e308`). One hostile config aborts the spawned automation run task with a panic (measured: "cannot convert float seconds to Duration: value is negative"). **Fix:** a `safe_duration_from_secs` guard that saturates instead of panicking (NaN/±inf/negative → `Duration::ZERO`, matching HA's lenient "non-positive delay = no delay"; absurdly large → clamped to ~100 years). Pinned by `delay_negative_seconds_does_not_panic`, `delay_nan_seconds_does_not_panic`, `delay_infinite_seconds_does_not_panic`, `wait_for_trigger_negative_timeout_does_not_panic`, `safe_duration_saturates_hostile_values` (incl. overflow clamp).
-
-**Dimensions confirmed clean (with evidence):**
- **Condition bypass / fail-closed eval** — a `Condition::Template` whose render errors evaluates to `false` (`condition.rs` `Err(_) => false`), and a `Choose` branch condition that fails to deserialize is treated as **non-matching** (the branch is skipped), not silently passing (`action.rs` `ChoiceBranch::matches` `Err(_) => return false`). Both fail **closed** (do-not-run), confirmed by the existing `choose_*` tests and template-false-blocks-action behavioral test. No true-by-default-on-parse-error path found.
- **Re-entrancy / livelock (DoS)** — run-mode machinery is bounded and tested: `Single`/`IgnoreFirst` re-entrancy guard, `Restart` cancel-and-replace, `Queued` FIFO serialization, and `max: N` semaphore cap (ADR-162; `restart_mode_cancels_prior_run`, `queued_mode_runs_sequentially_not_concurrently`, `max_two_caps_concurrency_at_two`, `single_mode_does_not_double_fire_on_rapid_triggers`). A self-triggering automation does not livelock the engine — each fire is bounded by its run-mode.
- **Action authorization** — templates are read-only sandboxed (`states`/`state_attr`/`is_state`/`now` globals; no service-call or state-set global is exposed to template scope), so a template cannot escalate into an action. Service authorization itself is enforced at the `homecore` service-registry boundary (out of this crate's scope); no gap found in what the automation crate enforces.
- **Panic-on-config (parse)** — `serde_yaml`/`serde_json` deserialization returns structured `AutomationError` (no `unwrap`/`expect`/index reachable from a crafted config in the eval/exec path); the only remaining panic surface was the `from_secs_f64` path fixed as HC-SEC-02.
-
-Validation: `cargo test -p homecore-automation --no-default-features` → 54 passed / 0 failed (+14 over baseline). Python deterministic proof unchanged (homecore-automation is off the signal-processing proof path).
-
---
-
 ## 9. References

 ### HA upstream
@@ -1,444 +0,0 @@
-# ADR-131: HOMECORE-UI — Operational dashboard for the two-tier Cognitum stack
-
-| Field | Value |
-|-------|-------|
-| **Status** | Accepted — UI implemented (§10); full backend wiring specified (§11–§12) |
-| **Date** | 2026-06-14 |
-| **Deciders** | ruv |
-| **Codename** | **HOMECORE-UI** — first-class operator dashboard inside the Cognitum Appliance shell |
-| **Relates to** | [ADR-126](ADR-126-ruview-native-ha-port-master.md) (HOMECORE master), [ADR-127](ADR-127-homecore-state-machine-rust.md) (HOMECORE-CORE state machine), [ADR-128](ADR-128-homecore-integration-plugin-system.md) (HOMECORE-PLUGINS), [ADR-129](ADR-129-homecore-automation-engine.md) (automation engine), [ADR-130](ADR-130-homecore-rest-websocket-api.md) (HOMECORE-API), [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) (recorder/semantic search), [ADR-151](ADR-151-room-calibration-specialist-training.md) (room calibration HTTP API), [ADR-100](ADR-100-cog-packaging-specification.md) (Cog packaging), [ADR-116](ADR-116-cog-ha-matter-seed.md) (cog-ha-matter), [ADR-069](ADR-069-cognitum-seed-csi-pipeline.md) (SEED RVF ingest), [ADR-105](ADR-105-federated-csi-training.md) (federated CSI training) |
-| **Tracking issue** | TBD |
-| **Parent** | [ADR-126](ADR-126-ruview-native-ha-port-master.md) (sub-ADR, HOMECORE-127…134 family) |
-
---
-
-## 1. Context
-
-HOMECORE (ADR-126 through ADR-134) is the native Rust + WASM + TypeScript port of Home Assistant running as the hub on the Cognitum v0 Appliance. As of P2, the state machine ([ADR-127](ADR-127-homecore-state-machine-rust.md)), API ([ADR-130](ADR-130-homecore-rest-websocket-api.md)), and COG runtime ([ADR-128](ADR-128-homecore-integration-plugin-system.md)) are in place. What is missing is a first-class dashboard UI that operators, integrators, and residents can use to manage the full two-tier hardware stack that HOMECORE coordinates.
-
-### 1.1 The two-tier hardware model this UI must represent
-
-This is the most important architectural constraint the UI must carry through every panel:
-
- **Cognitum SEED** — a Pi Zero 2 W-based edge node. It has its own RVF vector store (8-dim, content-addressed, with kNN queries), Ed25519 witness chain, SHA-256 ingest audit trail, onboard environmental sensors (BME280 temperature/humidity/pressure, PIR motion, reed switch, ADS1115 4-channel ADC, vibration), 13 drift detectors, an MCP proxy (114 tools, JSON-RPC 2.0, default-deny policy), 98 HTTPS API endpoints, and epoch-based swarm sync for multi-SEED deployments. SEEDs sit close to the ESP32 sensing nodes and receive feature vectors from them at 1 Hz. Multiple SEEDs can form a peer mesh. **This is the sensing and memory tier.**
- **Cognitum v0 Appliance** — a Pi 5 + Hailo-10H hub, running at `:9000`. It hosts the COG runtime (`/var/lib/cognitum/apps/`), the HOMECORE state machine and event bus, the calibration service, `ruview-mcp-brain:9876`, `cognitum-rvf-agent:9004`, `ruvector-hailo-worker:50051`, and acts as the fleet coordinator for multi-room correlation and federated training. The Appliance is where HOMECORE runs, and it is what the dashboard user is sitting in front of. **This is the computation and orchestration tier.**
-
-SEEDs are **subordinate nodes that the Appliance supervises** — they are not peers. The UI navigation hierarchy must reflect this: the Appliance is the root, SEEDs are children, ESP32 nodes are leaves.
-
-### 1.2 What the UI is not
-
-HOMECORE-UI is **not** a re-skin of the existing Cognitum Cog Store. It is a full operational dashboard that **extends** the Cognitum platform's shell — the Cog Store, API Explorer, and Guide already exist and must remain intact, with the HOMECORE dashboard added as a first-class navigation section alongside them.
-
---
-
-## 2. Decision
-
-Build HOMECORE-UI as a **complete** TypeScript + Rust→WASM frontend (per this ADR's §3 and the HOMECORE-127…134 family) that:
-
-1. Lives at `http://cognitum-v0:9000/homecore` (or as a dedicated nav item in the Cognitum Appliance shell).
-2. Is visually and stylistically seamless with the existing Cognitum platform — same dark theme, same design tokens, same component patterns as `https://seed.cognitum.one/store`.
-3. Drives the HOMECORE REST + WebSocket API ([ADR-130](ADR-130-homecore-rest-websocket-api.md)) and the calibration HTTP API ([ADR-151](ADR-151-room-calibration-specialist-training.md)) for all data.
-4. Updates in real-time via the homecore `subscribe_events` WebSocket channel. **The UI must never poll for entity state.**
-
-**This is a decision to deliver the complete operational dashboard — every panel in §4.1 through §4.10, every navigation section in §5, fully wired to live data — not a design-system scaffold or a partial first cut.** A static layout shell with placeholder data is explicitly **out of scope as a deliverable**: the design system (§3) is a means to the complete UI, not an end in itself. The acceptance bar for this ADR is that an operator can drive the full two-tier stack — fleet, entities, rooms, COGs, calibration, events, audit, and settings — from the dashboard, against real APIs, with no panel left as a stub.
-
-### 2.1 `homecore-server` is the single backend-for-frontend (BFF) gateway
-
-The data the dashboard needs is spread across **three backend tiers that are not one process**: (a) `homecore-api` (`/api/*` REST + `/api/websocket`, mounted in `homecore-server`); (b) the **calibration API** (`/api/v1/*`, served by a *separate* binary — `wifi-densepose calibrate-serve` / `wifi-densepose-sensing-server`); and (c) the **SEED device tier + appliance daemons** (RVF vector store, witness chain, onboard sensors, reflex rules, COG supervisor, federation), which are physically separate HTTPS services on the SEED nodes and the appliance.
-
-The browser must talk to **exactly one origin.** Therefore `homecore-server` is promoted to the **single BFF / API gateway** for HOMECORE-UI: it serves the static assets at `/homecore`, serves `homecore-api` at `/api/*`, and **adds a new `/api/homecore/*` namespace** that proxies and aggregates the calibration API and the SEED/appliance tiers server-side. The UI only ever issues same-origin requests; cross-service auth (SEED bearer tokens, calibration tokens) is held by the gateway and **never exposed to the browser**. This collapses the CORS/multi-port problem and gives one place to enforce the long-lived-access-token auth (§4.10).
-
-### 2.2 No mock data in production
-
-The in-browser mock layer that the first UI cut shipped behind DEMO banners (§7.1, prior revision) is **demoted to a dev-only fixture** gated behind an explicit `?demo=1` / `HOMECORE_UI_DEMO=1` flag. The production build wires **every** panel to a real gateway endpoint. The full endpoint contract and the backend work each panel needs are specified in **§11**; the staged path to get there is **§12**. A panel may show an empty/typed-error state when its upstream is down, but it must never silently render fabricated data.
-
---
-
-## 3. Design system — Cognitum platform conventions
-
-The implementor **must study `https://seed.cognitum.one/store` as the definitive design reference before writing a single line of CSS.** The existing platform's design tokens, extracted from production, are:
-
-### 3.1 Colour palette (CSS custom properties)
-
-| Token | Value | Role |
-|---|---|---|
-| `--bg` | `#0a0e1a` | page background (very dark navy) |
-| `--bg2` | `#111627` | secondary background / nav strip |
-| `--card` | `#171d30` | card / panel surface |
-| `--card-h` | `#1e2540` | card hover state |
-| `--border` | `#252d45` | all border strokes (≈0.67px, subtle) |
-| `--t1` | `#e0e4f0` | primary text (near-white) |
-| `--t2` | `#8890a8` | secondary / muted text |
-| `--t3` | `#505872` | tertiary / disabled text |
-| `--cyan` | `#4ecdc4` | primary action colour (Install buttons, live indicators, accents) |
-| `--cyan-d` | `rgba(78,205,196,0.15)` | cyan tint background for status badges |
-| `--green` | `#6bcb77` | success / online / healthy states |
-| `--green-d` | `rgba(107,203,119,0.15)` | green tint background |
-| `--amber` | `#d4a574` | warning / stale / degraded states |
-| `--amber-d` | `rgba(212,165,116,0.15)` | amber tint background |
-| `--red` | `#e06060` | error / offline / veto states |
-| `--red-d` | `rgba(224,96,96,0.15)` | red tint background |
-| `--purple` | `#a78bfa` | informational / epoch / chain indicators |
-| `--purple-d` | `rgba(167,139,250,0.15)` | purple tint background |
-| `--r` | `10px` | standard border radius on all cards and panels |
-
-### 3.2 Typography
-
- `--font`: `'Segoe UI', system-ui, -apple-system, sans-serif` — all body and heading text.
- `--mono`: `'Cascadia Code', 'Fira Code', Consolas, monospace` — all entity IDs, API endpoints, hex values, JSON payloads, COG binary hashes.
-
-### 3.3 Component patterns (from the live Cog Store and API Explorer)
-
- **Cards**: `background: var(--card)`, `border: 0.67px solid var(--border)`, `border-radius: var(--r)`, `padding: 24px`.
- **Category pills / status badges**: small `border-radius: 4–6px`, uppercase text, coloured background tint (e.g. `background: var(--cyan-d); color: var(--cyan)` for `RUNNING`; `background: var(--amber-d); color: var(--amber)` for `STALE`).
- **Primary action buttons**: `background: var(--cyan)`, `color: var(--bg)`, no border — matching the existing "Install" button style exactly.
- **Secondary / ghost buttons**: transparent background, `border: 1px solid var(--border)`, `color: var(--t1)` — matching the existing "Details" button style.
- **Nav strip**: `background: var(--bg2)`, text items in `--t2`, active item highlighted in `--cyan` with a bottom underline.
- **Featured card gradient borders**: top-edge linear gradient from `var(--cyan)` to `var(--purple)` — replicate for HOMECORE section headers.
- **Live metric cards** (API Explorer status page): icon + large numeric value in `--cyan` or `--green`, label in `--t2` below, on a `var(--card)` background.
- **Method badge pills** on the API Explorer (`GET` in green, `POST` in amber, `AUTH` in purple) — reuse this same pill system for COG status indicators.
-
-The implementor **must not introduce new colours, typefaces, or border radii.** Every component should feel like it was built by the same team that built the Cog Store and the API Explorer. A user navigating from the Cog Store into the HOMECORE dashboard should not notice a visual seam.
-
---
-
-## 4. UI sections — required panels
-
-### 4.1 System Dashboard (the "home screen")
-
-The always-visible overview panel. Modelled on the API Explorer's live metric cards. All values update in real-time.
-
- **v0 Appliance health strip** — reuse the exact metric-card pattern from `seed.cognitum.one/status`: one card each for CPU %, RAM usage, Hailo-10H inference load (% utilisation), Hailo temperature, uptime, and the running services (`ruview-mcp-brain:9876`, `cognitum-rvf-agent:9004`, `ruvector-hailo-worker:50051`). Values in `--cyan`, labels in `--t2`. This strip is always at the top — it represents the machine the user is looking at.
- **SEED Fleet overview** — a grid of SEED node cards (one per paired SEED) on the `var(--card)` surface with `var(--border)`. Each card shows: online/offline status pill (green/red), firmware version, epoch number, current vector count, last ingest timestamp, and witness-chain validity badge. A collapsed row shows the SEED's 5 onboard sensors in summary (PIR: yes/no, door: open/closed, temperature from BME280). Offline SEEDs render the entire card with a `--red-d` background tint. Clicking a SEED card navigates to the SEED Detail view (§4.2).
- **ESP32 Node summary** — count of active ESP32 nodes per SEED, current frame rate (target: 100 Hz CSI + 1 Hz feature vectors), and a compact warning list for nodes with known issues (presence_score normalisation anomaly, stale firmware version).
- **COG Runtime status row** — a horizontal strip of status pills for each installed COG on the v0 Appliance. Pill colours follow the existing badge convention: `--green-d`/`--green` for running, `--red-d`/`--red` for failed, `--t3`/`--t2` for stopped. COG name in `--mono`. Clicking a pill navigates to COG Management (§4.6).
- **Event Bus activity indicator** — a small real-time sparkline showing the homecore broadcast channel event rate (events/sec). Indicate channel lag if a subscriber is falling behind the 4,096-event capacity.
-
-### 4.2 SEED Detail View (per-SEED drill-down)
-
-Accessible from the fleet grid. Full-page panel for a single SEED node, using the card + section-header pattern from the Cog Store's detail views.
-
- **SEED identity header** — `device_id` in `--mono`, firmware version, paired status in green, USB vs WiFi connection mode. A section-header gradient border (cyan → purple, matching the featured card style) visually separates this from Appliance content.
- **Vector Store panel** — current vector count, dimension (8), last kNN query latency, current epoch number, a small sparkline of ingest rate over the last hour, and a storage budget bar showing usage against the 100K working-set target. A "Compact now" button (`POST /api/v1/store/compact`) in ghost style. When usage exceeds 80%, the bar renders in `--amber`.
- **Witness Chain panel** — chain length (SHA-256 entries), last verification timestamp, a one-click "Verify chain" button (`POST /api/v1/witness/verify`), and an "Export attestation bundle" button for regulated deployments. The Ed25519 custody attestation (device-bound keypair, epoch + vector count + witness head) renders here. Chain length in `--purple`, following the existing epoch/chain colour convention.
- **Onboard Sensors panel** — live readings from all 5 sensors in individual sub-cards: BME280 (temperature °C, humidity %, pressure hPa), PIR (motion boolean with last-triggered timestamp), reed switch (open/closed with last-changed timestamp), ADS1115 (4 analog channels with configurable labels), vibration (boolean with last-triggered). These are ground-truth validators against CSI readings and are critical for diagnosing false positives in the mixture-of-specialists. Sensor values in `--cyan`; sensor names in `--t2`.
- **Reflex Rules panel** — the 3 pre-configured rules with current state: `fragility_alarm` (threshold 0.3 → relay actuator), `drift_cutoff` (threshold 1.0), `hd_anomaly_indicator` (threshold 200 → PWM brightness). Show last-fired time for each. The `fragility_alarm` threshold is the most commonly adjusted field and should be editable inline. Rules that have recently fired render with a `--amber-d` background tint.
- **Cognitive Analysis panel** — boundary fragility score (0.0–1.0, from Stoer-Wagner min-cut on the kNN graph) rendered as a progress bar: green below 0.3, amber 0.3–0.6, red above 0.6. High fragility (>0.3) indicates a regime change in the environment and should be visually prominent. Temporal coherence phase boundaries shown as a labelled timeline of detected environment state transitions. kNN graph rebuild cadence indicator (every 10 s).
- **Ingest pipeline status** — which ESP32 nodes feed this SEED, the packet type each is sending (`0xC5110003` native feature vectors vs `0xC5110002` vitals fallback path — distinguished visually since native is preferred), current ingest batch size, flush interval, and bridge path topology (direct vs host-laptop hop). The bridge-hop warning (known architectural limitation) renders in `--amber` since it adds a network hop.
-
-### 4.3 SEED Fleet Map (multi-SEED topology)
-
-For deployments with more than one SEED, a topology view showing the mesh:
-
- **Node hierarchy diagram** — v0 Appliance at root, SEEDs as second tier (grouped by room/zone), ESP32 nodes as leaves under each SEED. Lines represent active data flows. ESP-NOW mesh sync links between SEEDs shown as dashed lines. Connection health shown via line colour (green/amber/red). All labels in `--mono`.
- **Cross-SEED event deduplication indicator** — for events that span multiple SEEDs (one fall detected by two rooms; one occupant tracked through room A → hallway → room B), show a fusion badge indicating how many SEEDs contributed to the composite event.
- **Federation config** ([ADR-105](ADR-105-federated-csi-training.md)) — federated-learning round coordinator role (which SEED is the round coordinator), current round number, K healthy nodes selected, delta exchange status. **Model deltas only — never raw CSI** is a design invariant that must be labelled explicitly in the UI.
-
-### 4.4 Entity & State Browser
-
-The homecore state machine (`DashMap<EntityId, Arc<State>>`) is the authoritative source of truth. Every COG running on the v0 Appliance contributes entities.
-
- **Entity list by domain** — grouped by the `domain.` prefix of `EntityId`, using collapsible section headers. The 21 entities per ESP32 node (11 raw + 10 semantic primitives from `cog-ha-matter`) are the most important set. For each entity: current state string (in `--t1`), last-changed timestamp (in `--t3`), attribute map as collapsible JSON in `--mono`, and the Context (`user_id` + `parent_id` causality chain, critical for care/audit deployments). Entity IDs always in `--mono`.
- **SEED provenance badge** — each entity carries a small badge showing its data lineage: which ESP32 node → which SEED → which COG → homecore state machine. This trace is invaluable for debugging false positives and is a **first-class UI element, not a collapsed detail.**
- **Domain filter + semantic search** — filter by domain prefix and, once [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) (homecore-recorder) lands, ruvector-backed semantic search: "when did the living room anomaly score last correlate with a door-open event?" A keyword filter across entity IDs and attribute keys ships in the initial release regardless of [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) status, given entity density; the semantic search layers on top once the recorder lands.
- **Real-time WebSocket feed** — entity states update live via the homecore `subscribe_events` WebSocket command ([ADR-130](ADR-130-homecore-rest-websocket-api.md)). The UI must never poll. Show a broadcast-channel lag indicator; warn visually if the subscriber is falling behind the 4,096-event channel capacity.
- **StateChanged detail panel** — clicking any entity opens a slide-over panel showing the full `StateChangedEvent`: `old_state`, `new_state`, `context.id`, `context.user_id`, and the `context.parent_id` chain rendered as a breadcrumb trail.
-
-### 4.5 RoomState / Sensing Panel
-
-Surfaces the mixture-of-specialists output from the calibration service — the highest-level per-room sensing result. Data comes from `GET /api/v1/room/state?bank=<room_id>` on the v0 Appliance.
-
- **Per-room cards** — one card per `room_id` on the `var(--card)` surface. Each card shows live `RoomState` JSON fields as sub-rows: presence (occupied/absent chip in green/red with confidence bar), posture (standing/sitting/lying chip with confidence), breathing BPM (numeric in `--cyan` with range indicator 6–30), heart rate BPM (numeric in `--cyan` with range indicator 40–120), restlessness score (0–1 progress bar), and anomaly score (0–1 with normal/anomalous label, bar turns red above a configurable threshold).
- **STALE warning** — when `stale: true` (the specialist bank was trained against a different baseline), render the entire room card with a `--amber-d` background tint and a prominent amber banner reading "Bank stale — baseline has changed" with a direct "Recalibrate room" link into the calibration wizard (§4.7). This is the most common real-world failure mode and **must never be subtle.**
- **VETO indicator** — when `vetoed: true` (anomaly veto suppressed vitals/posture because the window was physically implausible), render the affected specialist slots in `--red` with a "Veto active" label. Values suppressed by veto **must not render as zeros** — they must render as explicitly withheld.
- **Null specialist placeholders** — specialists not yet trained (`null` in the specialist bank) render as "Not trained" placeholders in `--t3` with a small "Calibrate to enable" prompt in ghost style. They are **not** errors.
- **Confidence bars** — each specialist output has a confidence float, shown as a small inline bar (`--cyan` fill) next to the reading. Low confidence (< 0.4) renders the bar in `--amber`.
- **Multi-SEED fusion indicator** — for rooms served by multiple SEEDs, show a small badge indicating how many SEED nodes contributed to the `MultiNodeMixture` for this room's reading.
-
-### 4.6 v0 Appliance COG Management
-
-The v0 Appliance hosts COGs at `/var/lib/cognitum/apps/`. This panel is the operational companion to the existing Cog Store (`seed.cognitum.one/store`). It must match the Cog Store's visual conventions precisely — same card layout, same category pills, same install/detail button pair — because operators will move between the two surfaces.
-
- **Installed COGs list** — for each COG: `id` and `version` in `--mono`, architecture badge (`arm`/`hailo10` etc., category-pill pattern), status pill (running/stopped/failed/updating in green/grey/red/amber), `binary_sha256` verified badge (Ed25519 signature verification shown as a shield icon in `--green` or `--red`), and PID from the pid file. Actions: start, stop, restart (ghost style), and view `output.log` / `error.log` in a monospace drawer using `--mono`. Edit `config.json` inline with syntax highlighting.
- **COG Store / App Registry** — browsable `app-registry.json` listing. This panel should visually mirror `seed.cognitum.one/store` as closely as possible — same featured-card hero layout, same icon + title + description + category pill + action button structure. One-click install downloads the binary from GCS, verifies `binary_sha256` + `binary_signature`, writes the manifest, and starts the COG. Show which new homecore entities will appear in the state machine after install, as a preview list before confirming.
- **OTA Updates** — a badge count on installed COGs with available updates, matching the "Installed (N)" tab badge convention from the existing Cog Store. Show a diff panel (version change, new entities, config schema changes) before confirming the update.
- **Hailo HEF status** — for COGs with `arch: hailo10`: loaded HEF files on the Hailo-10H, current inference throughput, and `ruvector-hailo-worker:50051` connection status. The RF Foundation Encoder ([ADR-150](ADR-150-rf-foundation-encoder.md)) and neural pose head display here once available.
-
-### 4.7 Calibration Wizard
-
-The full baseline → enroll → train → verify pipeline runs via HTTP against the v0 Appliance ([ADR-151](ADR-151-room-calibration-specialist-training.md)). This is a multi-step guided flow — not a raw API panel. Use a stepped wizard layout with a progress indicator at the top (steps 1–5 as numbered pills, active step in `--cyan`, completed in `--green`, pending in `--t3`).
-
- **Step 1 — Select room and SEED** — enter a `room_id` name (validated against `[A-Za-z0-9_-]{1,64}`) and select which SEED(s) and ESP32 nodes serve this room from a dropdown populated from the live fleet. Show current CSI ingest health for the selected nodes inline — if frames are not arriving at the expected rate, display an amber warning **before** allowing the operator to proceed. A broken ingest pipeline will silently fail calibration.
- **Step 2 — Baseline capture** — `POST /api/v1/calibration/start`. A large full-width animated progress bar (cyan fill) reads from `GET /api/v1/calibration/status`: frames recorded vs target, ETA in seconds, `z_median` value. If `motion_flagged` is true, overlay an amber banner: "Room must be empty — movement detected." The baseline UUID produced here is the anchor for all future STALE detection for this room — display it in `--mono` once complete so operators can record it.
- **Step 3 — Anchor enrollment** — the 8 anchor labels in enforced order: `empty`, `stand_still`, `sit`, `lie_down`, `breathe_slow`, `breathe_normal`, `small_move`, `sleep_posture`. For each: a human-readable instruction with an illustration, a countdown timer rendered as a circular progress ring in `--cyan`, and an immediate quality-gate result (accepted in green, retry in amber with a reason string). Drive via `POST /api/v1/enroll/anchor` + `GET /api/v1/enroll/status`. After each accepted anchor, show the extracted feature values (mean, variance, breathing_score, heart_score) in a small `--mono` data row so operators can sanity-check the capture. Show overall progress as "N / 8 anchors accepted."
- **Step 4 — Train** — a single `POST /api/v1/room/train` call. Show the 6 specialist results as a checklist: presence (threshold + occupied_var), posture (prototype count), breathing (min_score), heartbeat (min_score), restlessness (calm/active motion values), anomaly (prototype count + scale). Specialists that returned non-null render in `--green`. Null specialists (insufficient anchor data) render in `--amber` with a "Re-enroll missing anchors" prompt linking back to Step 3 for the specific missing labels.
- **Step 5 — Verify live** — display the live `RoomState` for the just-trained room using the same per-room card layout as §4.5. Prompt the operator to stand in the room and verify presence is detected, try sitting/lying to confirm posture, and breathe normally to confirm vitals are in plausible range. A "Confirm and save" button (cyan, primary) closes the wizard; a "Something's wrong — re-enroll" button (ghost) loops back to Step 3.
-
-### 4.8 Event Bus & Automation Feed
-
- **Live event stream panel** — a virtualized scrolling list of `SystemEvent` variants (`StateChanged`, `EntityRegistered`, `ConfigReloaded`) and notable `DomainEvent`s from the homecore Tokio broadcast channel. Each row shows: event-type pill (coloured by variant), `entity_id` in `--mono`, old state → new state arrow, timestamp, and `context.user_id`. The stream is filterable by entity domain, event type, or source SEED/COG. The filter bar uses the same search-input style as the Cog Store's search field.
- **Context causality breadcrumb** — expanding any event row shows the full Context chain (`context.id` → `parent_id` → `grandparent_id`) as a breadcrumb trail in `--mono`. This is how automation loops become visible without any separate debugging tool.
- **Automation builder** ([ADR-129](ADR-129-homecore-automation-engine.md) scope) — a trigger → condition → action editor on the card surface. The most important RuView-specific trigger types to support are: `state_changed` on `RoomState` entities with a threshold expression (e.g. `anomaly.value > 0.8`), SEED reflex-rule firing events (`fragility_alarm`, `hd_anomaly_indicator`), and custom `domain_event` topics. Actions include calling services in the homecore service registry and firing domain events. The condition expression editor uses `--mono`.
-
-### 4.9 Witness / Audit Log
-
- **Unified witness timeline** — a chronological merged view of events from both tiers: the SEED's SHA-256 ingest chain (every RVF store write attested) and homecore's Ed25519 state-transition chain (biometric crossings, BFLD identity-risk elevations). Each row: `entity_id` in `--mono`, old/new state, timestamp, source SEED `device_id`, signing key fingerprint (first 8 chars in `--mono`). Pagination uses the same "Showing X–Y of Z" convention from the Cog Store's cog grid.
- **Privacy mode banner** — a persistent top-of-panel banner showing current privacy mode: `--green-d`/green text for full-publish mode; `--amber-d`/amber text for audit-only mode (SHA-256 digests on-SEED only, no MQTT state messages). Show the per-SEED privacy mode state, since SEEDs can be individually configured. Toggling privacy mode is a high-stakes action — require an explicit "Confirm" step with a summary of what will change.
- **Export bundle** — an "Export attestation bundle" button (ghost) that packages the SEED witness chain + homecore Ed25519 chain as a downloadable archive for regulated-deployment (care home, hotel, shared office) compliance handoff.
-
-### 4.10 Settings & Integration Config
-
- **SEED fleet management** — add, remove, and reprovision SEEDs. Show the USB-only pairing requirement prominently (the pairing window only opens via `169.254.42.1`, not WiFi — a security invariant). Per-SEED: `device_id` in `--mono`, firmware version, bearer token status, and a "Rotate token" action (ghost) that walks the operator through the secure token rotation flow.
- **ESP32 node provisioning** — per-node NVS config display (target IP, target port, node_id), last-seen firmware version, and a link to the provisioning script. The `node_id` → room/zone assignment is editable here and persists to the room calibration system's `room_id` mapping.
- **MQTT / cog-ha-matter config** ([ADR-116](ADR-116-cog-ha-matter-seed.md)) — broker URL, credentials (masked), MQTT topic prefix, mDNS advertisement status (`_ruview-ha._tcp`), and a live connection indicator (green dot for connected, red for unreachable). The 21 HA-DISCO entities per node are listed here with their `via_device` assignments showing which SEED they belong to in HA's device registry.
- **Long-lived access tokens** — for homecore-api companion-app connections (HA 2025.1 wire-compat, [ADR-130](ADR-130-homecore-rest-websocket-api.md)). Token creation, last-used timestamp, and revocation. The HA companion-app pairing QR-code flow surfaces here.
- **Federation config** — for multi-SEED deployments: ESP-NOW mesh sync status, cross-SEED epoch alignment values, and federated-learning round settings (coordinator SEED, round cadence, Krum aggregation parameters per [ADR-105](ADR-105-federated-csi-training.md)). The design invariant **"model deltas only, never raw CSI"** must be labelled explicitly in this panel.
-
---
-
-## 5. Navigation structure
-
-HOMECORE-UI must integrate into the existing Cognitum Appliance nav shell. The top nav should read:
-
-```
-Framework | Guide | Cog Store | HOMECORE | Status
-```
-
-— inserting **HOMECORE** as a first-class nav item between the existing "Cog Store" and "Status" entries, using the same nav-item style (text in `--t2`, active state in `--cyan` with bottom underline).
-
-Within the HOMECORE section, a left sidebar (or top sub-nav on narrow viewports) provides section navigation:
-
-```
-Dashboard | SEED Fleet | Entities | Rooms | COGs | Calibration | Events | Audit | Settings
-```
-
-The COG Store panel within HOMECORE (§4.6) links out to `seed.cognitum.one/store` for the full catalog view, ensuring the existing Cog Store remains the canonical browsing experience.
-
---
-
-## 6. Key UX invariants
-
-These must be maintained across every panel:
-
-1. **Always make the tier origin of any data explicit.** A `RoomState` reading traces to an ESP32 node → SEED → COG → v0 Appliance state machine. The provenance badge (§4.4) must appear wherever entity states are displayed.
-2. **The `stale` and `vetoed` flags from `RoomState` and the kNN fragility score from SEED cognitive analysis are meaningful diagnostic signals** — they must never be silently hidden, styled grey-on-grey, or collapsed behind an expand toggle. They represent system health operators need to act on.
-3. **Values that are `null` because a specialist has not been trained must be visually distinct from values that are unavailable due to an error.** The distinction is operationally important: `null` means "calibrate to enable," unavailable means "investigate."
-4. **All entity IDs, hashes, API endpoints, binary signatures, device UUIDs, and JSON payloads must use `--mono` font.** This is already the convention in the API Explorer and must be consistent throughout HOMECORE-UI.
-5. **The v0 Appliance Hailo HAT is a separate subsystem from the SEED's edge compute.** Inference results tagged as Hailo-sourced (COGs with `arch: hailo10`) must be visually distinguished from results from CPU-only COGs (`arch: arm`) so operators can triage hardware-specific failures.
-
---
-
-## 7. Scope — complete UI delivery
-
-The deliverable is the **entire** dashboard. Every panel below ships fully implemented and wired to its live data source — there is no scaffold-only milestone and no panel left as a placeholder. The table records each panel's authoritative backing API so the build can proceed in whatever order best fits the dependency graph; it is a dependency map, **not** a sequence of partial releases.
-
-| Panel | Section | Backing API / source |
-|---|---|---|
-| System Dashboard | §4.1 | [ADR-130](ADR-130-homecore-rest-websocket-api.md) WebSocket + appliance health endpoints |
-| SEED Detail View | §4.2 | SEED HTTPS API (vector store, witness, sensors, reflex, cognitive analysis) |
-| SEED Fleet Map | §4.3 | fleet topology + federation ([ADR-105](ADR-105-federated-csi-training.md)) |
-| Entity & State Browser | §4.4 | [ADR-127](ADR-127-homecore-state-machine-rust.md) state machine via [ADR-130](ADR-130-homecore-rest-websocket-api.md) `subscribe_events`; semantic search via [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) |
-| RoomState / Sensing | §4.5 | [ADR-151](ADR-151-room-calibration-specialist-training.md) `GET /api/v1/room/state` |
-| COG Management | §4.6 | [ADR-128](ADR-128-homecore-integration-plugin-system.md) plugin runtime + [ADR-100](ADR-100-cog-packaging-specification.md) app registry |
-| Calibration Wizard | §4.7 | [ADR-151](ADR-151-room-calibration-specialist-training.md) calibration HTTP API |
-| Event Bus & Automation | §4.8 | [ADR-130](ADR-130-homecore-rest-websocket-api.md) broadcast channel + [ADR-129](ADR-129-homecore-automation-engine.md) automation engine |
-| Witness / Audit Log | §4.9 | SEED SHA-256 ingest chain + homecore Ed25519 chain |
-| Settings & Integration | §4.10 | SEED provisioning, [ADR-116](ADR-116-cog-ha-matter-seed.md) MQTT/Matter, LLAT, federation |
-
-### 7.1 Build sequencing within the complete deliverable
-
-The complete UI depends on backing services that mature on their own timelines. Each panel is built against the **real gateway endpoint** defined in §11; where the upstream is not yet available the panel renders a typed empty/error state, **not** fabricated data (the dev-only `?demo=1` fixture of §2.2 exists for offline development only and is never the shipped behaviour). Concretely, the hard contract dependencies are: [ADR-130](ADR-130-homecore-rest-websocket-api.md) (REST + WebSocket), [ADR-127](ADR-127-homecore-state-machine-rust.md) (state machine), [ADR-151](ADR-151-room-calibration-specialist-training.md) (calibration), [ADR-128](ADR-128-homecore-integration-plugin-system.md) (plugin runtime), [ADR-129](ADR-129-homecore-automation-engine.md) (automation), [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) (event history + semantic search), [ADR-116](ADR-116-cog-ha-matter-seed.md) (SEED/Matter), [ADR-069](ADR-069-cognitum-seed-csi-pipeline.md) (SEED ingest), and [ADR-105](ADR-105-federated-csi-training.md) (federation). The keyword entity filter (§4.4) ships immediately; semantic search layers on once [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) lands. The exact panel→endpoint→upstream map and the new gateway code each requires are §11; the staged delivery is §12.
-
---
-
-## 8. Consequences
-
-### 8.1 Positive
-
- Operators, integrators, and residents get a single coherent surface for the full two-tier stack, replacing the need to SSH into SEEDs or hand-craft API calls.
- The dashboard reuses the proven Cognitum design tokens and component patterns verbatim, so it ships visually consistent with no separate design effort and no perceptible seam between surfaces.
- Diagnostic signals that today are invisible (`stale`/`vetoed` flags, kNN fragility, provenance lineage, channel lag) become first-class, surfacing the system's most common real-world failure modes directly to operators.
-
-### 8.2 Negative / risks
-
- The UI hard-depends on the wire-compat guarantees of ADR-130 and the calibration contract of ADR-151; schema drift in either breaks panels silently. Integration tests against every backing contract in §7 are required.
- Committing to the complete UI in one deliverable is a larger up-front effort and couples the UI's readiness to the maturity of multiple backing services (§7.1, §11). The mitigation is the BFF gateway (§2.1): each panel targets one same-origin endpoint, and the gateway absorbs upstream churn behind a stable contract.
- Promoting `homecore-server` to a gateway means it now **proxies cross-tier traffic** (calibration API, SEED HTTPS, appliance daemons). This adds a network hop, a place for upstream timeouts/partial failures to surface, and a server-side store of SEED bearer tokens that must be protected (§11.10). Each proxied route needs an explicit timeout + typed error mapping so one slow SEED cannot stall the dashboard.
- Several panels depend on data that only exists on **real hardware or new daemons** (SEED device tier, appliance host metrics, COG supervisor). Until those upstreams exist the corresponding gateway routes return `503 upstream_unavailable`; this is honest but means the dashboard is only as "live" as the tiers behind it (§11 classifies every endpoint by what it depends on).
- Faithfully mirroring `seed.cognitum.one/store` couples HOMECORE-UI to the external Cog Store's evolving design; token drift there must be tracked and re-synced.
- The two-tier mental model (Appliance root, SEED children, ESP32 leaves) must be enforced consistently; any panel that flattens or peers the tiers undermines the core architectural constraint.
-
---
-
-## 9. References
-
- `https://seed.cognitum.one/store` — primary design reference for all visual conventions.
- `https://seed.cognitum.one/status` — reference for live metric-card layout.
- [ADR-126](ADR-126-ruview-native-ha-port-master.md) — HOMECORE master ADR.
- [ADR-127](ADR-127-homecore-state-machine-rust.md) — HOMECORE-CORE state machine and entity registry.
- [ADR-128](ADR-128-homecore-integration-plugin-system.md) — HOMECORE-PLUGINS WASM COG substrate.
- [ADR-129](ADR-129-homecore-automation-engine.md) — HOMECORE automation engine.
- [ADR-130](ADR-130-homecore-rest-websocket-api.md) — HOMECORE-API REST + WebSocket wire-compat.
- [ADR-132](ADR-132-homecore-recorder-history-semantic-search.md) — homecore-recorder, history + semantic search.
- [ADR-100](ADR-100-cog-packaging-specification.md) — Cognitum Cog packaging specification (manifest.json, status values, on-device layout).
- [ADR-116](ADR-116-cog-ha-matter-seed.md) — cog-ha-matter (SEED cog, HA-DISCO entity surface, mDNS).
- [ADR-069](ADR-069-cognitum-seed-csi-pipeline.md) — ESP32 CSI → Cognitum SEED RVF ingest pipeline (SEED architecture detail).
- [ADR-105](ADR-105-federated-csi-training.md) — Federated CSI training (multi-SEED federation).
- [ADR-151](ADR-151-room-calibration-specialist-training.md) — Per-room calibration specialist training (calibration HTTP API).
- `v2/crates/homecore/src/` — state machine, entity, event, registry source.
- `docs/integration/calibration-appliance-integration.md` — calibration API contract and RoomState schema.
-
---
-
-## 10. Implementation status
-
-Implemented as a zero-dependency, no-build-step vanilla TS/JS + CSS frontend served by `homecore-server` at `/homecore` (the `rufield-viewer` "Axum + vanilla-JS" pattern). The complete deliverable per §2/§7 — all ten panels, fully rendered, wired to live data where the backing service exists and to a contract-conformant DEMO-flagged mock layer (§7.1) where it does not.
-
-**Location:** `v2/crates/homecore-server/ui/` — `css/tokens.css` (the §3.1 palette, verbatim) + `css/app.css` (§3.3 components); `js/{ui,api,ws,mock,app}.js` (shared helpers, REST client, `subscribe_events` WS client, mock layer, shell+router); `js/panels/*.js` (one module per §4 panel). Mounted via `tower-http` `ServeDir` in `homecore-server::build_app`, gated by `--ui-dir`/`HOMECORE_UI_DIR`.
-
-**Verification:**
- **Rust** — `#[cfg(test)] mod ui_tests` in `homecore-server/src/main.rs`: 5 integration tests (`tower::oneshot`) covering index, design tokens, all ten panel modules served, API coexistence, and mount-disable. *Written but not compiled in the authoring environment (no Rust toolchain present); run `cargo test -p homecore-server` on a Rust host before merge.*
- **Frontend** — `ui/` test suite under plain `node` (no npm install): `npm test` → import/export graph verifier (15 modules) + render-smoke (executes every panel against a DOM shim; 21 checks) + interaction suite (live WS patch, ws.js handshake/parse, calibration contract; 3 checks). **24/24 green.**
- **Benchmark** — `npm run bench`: total bundle **136.8 KB** uncompressed (**~37× smaller** than HA's ~5 MB Lit bundle, the ADR-126 §1.1 foil); slowest panel **1.5 ms/cold-render**.
-
-**Honest scope — current vs. target.** *Earlier cut:* the front-end was complete but only §4.4 Entities was wired to a real backend; the rest rendered from an in-browser mock. *This revision implements the §11 wiring:*
-
- **Front-end (§11.11) — DONE and verified.** `api.js` rewritten: all data accessors are async and call the §11.2 gateway routes; the mock layer is demoted to a dev-only fixture reachable **only** under `?demo=1` / `HOMECORE_UI_DEMO` (§2.2); every panel `await`s and renders a typed empty/error state on failure (no mock fallback in production). All ten panels converted (3 by hand, 7 via parallel agents). Verified under Node: 5 test files green — import graph, boot, render-smoke (22), interaction (3), **and a new prod-errors suite (13) that runs with demo OFF + gateway unreachable and asserts every panel renders an error state, never mock, never throws** (it caught and fixed a real unhandled-rejection in the events panel).
- **Gateway (§11.1–§11.6) — IMPLEMENTED, COMPILED, TESTED, RUN.** New `homecore-server/src/gateway.rs` (+`reqwest` dep, +CLI/env flags `--calibration-url`/`--calibration-token`/`--apps-dir`/`--gateway-timeout-ms`, merged into `build_app` via `gateway_router`). Real handlers: `/api/cal/*` reverse-proxy (W2), `GET /api/homecore/rooms` with the §11.3 RoomState adapter (W2), `GET /api/homecore/cogs` supervisor over the apps dir (W4), `GET /api/homecore/appliance` from `/proc` + port probes (W6). SEED-device/appliance-daemon routes (seeds, federation, witness, privacy, settings, automations, events-history, hailo, tokens — W3/W5) return a typed `503 upstream_unavailable` per §11.2. **Verified on Rust 1.89: `cargo test -p homecore-server --no-default-features` = 12/12 pass** (6 gateway + 6 UI mount). **Run live:** `GET /api/homecore/appliance` returns real `/proc` metrics + TCP service probes; unauth → `401`; `cogs` → `[]` with no apps dir; SEED-tier → typed `503`; and against a mock calibration upstream the `/api/cal/*` proxy passes through (`200`) and `GET /api/homecore/rooms` correctly adapts `RoomState` to the UI shape (`breathing`→`breathing_bpm`, `heartbeat:null`→`heart_bpm:null`, injected `anomaly.threshold`/`room_id`, `stale` passthrough). **Live testing caught + fixed one real bug** — a double-`v1` path in the `/api/cal/*` proxy URL.
-
-The endpoint-by-endpoint contract is **§11**; the staged plan and which endpoints depend on real SEED/appliance hardware vs. pure software is **§12**.
-
---
-
-## 11. Backend wiring — making every panel real
-
-This section is the authoritative contract for full functionality. It removes the mock layer from the production path (§2.2) by routing every panel through the `homecore-server` BFF gateway (§2.1). Each endpoint is classified by what it depends on:
-
- **EXISTS** — backend code already in this repo; gateway only proxies/adapts.
- **NEW-GW** — pure software the gateway itself implements (filesystem, `/proc`, process control, recorder query) — no new external service.
- **NEW-API** — a small HTTP wrapper to add to an existing in-repo crate (`homecore-api`, `homecore-automation`).
- **SEED-DEV** — depends on a SEED node's on-device HTTPS API (separate hardware/firmware).
- **APPLIANCE** — depends on an appliance daemon / accelerator stat source.
-
-### 11.1 Gateway shape
-
-`homecore-server` already mounts `homecore-api` at `/api/*` and the UI at `/homecore`. It gains a new **`/api/homecore/*`** namespace (the dashboard-specific aggregation surface) plus a **`/api/cal/*`** reverse-proxy to the calibration service. The browser issues only same-origin requests; the gateway fans out server-side, holding all upstream credentials (§11.10). Every proxied route has an explicit timeout and maps upstream failure to a typed body (`503 upstream_unavailable`, `504 upstream_timeout`) so one slow tier never stalls the dashboard.
-
-### 11.2 Master endpoint contract (panel → gateway route → upstream → status)
-
-| Panel | UI method (`api.js`) | Gateway route | Upstream / source | Class |
-|---|---|---|---|---|
-| §4.4 Entities | `states()` | `GET /api/states` | `homecore` state machine | **EXISTS** ✅ wired |
-| §4.4/§4.8 live feed | WS | `GET /api/websocket` (`subscribe_events`) | `homecore` event bus | **EXISTS** ✅ wired |
-| §4.8 Event history | `eventHistory(q)` | `GET /api/events?since=…` | `homecore-recorder` ([ADR-132](ADR-132-homecore-recorder-history-semantic-search.md)) | **NEW-API** |
-| §4.8 Automations | `automations()` / `saveAutomation()` | `GET/POST/DELETE /api/homecore/automations` | `homecore-automation` ([ADR-129](ADR-129-homecore-automation-engine.md)) | **NEW-API** |
-| §4.5 Rooms | `roomStates()` | `GET /api/homecore/rooms` → per-room `GET /api/cal/v1/room/state?bank=` | `calibrate-serve` ([ADR-151](ADR-151-room-calibration-specialist-training.md)) | **EXISTS** (proxy + adapter) |
-| §4.7 Calibration | `calibration.*` | `POST /api/cal/v1/calibration/{start,stop}`, `GET …/status`, `POST …/enroll/anchor`, `GET …/enroll/status`, `POST …/room/train` | `calibrate-serve` | **EXISTS** (proxy) |
-| §4.6 COGs | `cogs()` / `cogAction()` / `cogLogs()` | `GET /api/homecore/cogs`, `POST …/cogs/:id/{start,stop,restart}`, `GET …/cogs/:id/logs`, `GET/PUT …/cogs/:id/config` | COG supervisor over `/var/lib/cognitum/apps/` ([ADR-100](ADR-100-cog-packaging-specification.md)/[ADR-128](ADR-128-homecore-integration-plugin-system.md)) | **NEW-GW** |
-| §4.6 Hailo HEF | `hailo()` | `GET /api/homecore/hailo` | `ruvector-hailo-worker:50051` | **APPLIANCE** |
-| §4.1 Appliance health | `appliance()` | `GET /api/homecore/appliance` | host `/proc` + Hailo stats + service probes | **NEW-GW** (+APPLIANCE for Hailo) |
-| §4.1/§4.2 Fleet + SEED detail | `seeds()` / `seed(id)` | `GET /api/homecore/seeds`, `GET …/seeds/:id` | SEED device HTTPS API ([ADR-069](ADR-069-cognitum-seed-csi-pipeline.md)) via registry | **SEED-DEV** |
-| §4.2 SEED actions | `seedCompact()` / `seedVerify()` | `POST …/seeds/:id/{compact,witness/verify}` | SEED device API | **SEED-DEV** |
-| §4.3 Federation | `federation()` | `GET /api/homecore/federation` | federation coordinator ([ADR-105](ADR-105-federated-csi-training.md)) | **SEED-DEV/APPLIANCE** |
-| §4.9 Witness/Audit | `witnessLog(p,s)` | `GET /api/homecore/witness?page=…` | merge: `homecore` Ed25519 chain + per-SEED SHA-256 chains | **NEW-API + SEED-DEV** |
-| §4.9 Privacy mode | `privacyModes()` / `setPrivacy()` | `GET/POST /api/homecore/privacy` | SEED privacy control plane ([ADR-141](ADR-141-bfld-privacy-control-plane-modes-attestation.md)) + cog-ha-matter | **SEED-DEV** |
-| §4.9 Export bundle | `exportAttestation()` | `GET /api/homecore/witness/export` | gateway packages both chains | **NEW-GW** |
-| §4.10 Tokens (LLAT) | `tokens()` / `createToken()` / `revokeToken()` | `GET/POST/DELETE /api/homecore/tokens` | `homecore-api` `LongLivedTokenStore` | **NEW-API** |
-| §4.10 MQTT/Matter | `mqttConfig()` | `GET /api/homecore/integrations/mqtt` | cog-ha-matter config ([ADR-116](ADR-116-cog-ha-matter-seed.md)) | **NEW-GW/SEED-DEV** |
-| §4.10 ESP32 provisioning | `nodes()` / `assignRoom()` | `GET/PUT /api/homecore/nodes` | SEED ingest config ([ADR-069](ADR-069-cognitum-seed-csi-pipeline.md)) | **SEED-DEV** |
-| §4.10 SEED mgmt | `pairSeed()` / `rotateToken()` | `POST /api/homecore/seeds/{pair,:id/rotate-token}` | SEED pairing (USB `169.254.42.1`) | **SEED-DEV** |
-
-### 11.3 Calibration proxy + RoomState adapter
-
-The calibration service is real but on a different binary/port; the gateway reverse-proxies it under `/api/cal/*` (upstream base from `HOMECORE_CALIBRATION_URL`). Its `RoomState` (`wifi-densepose-calibration/src/runtime.rs`) does **not** match the UI's shape, so the gateway adapts it in `GET /api/homecore/rooms`:
-
-| Real field (`RoomState`) | UI field | Adapter rule |
-|---|---|---|
-| `breathing: Option<SpecialistReading>` | `breathing_bpm: {value,confidence}\|null` | rename; `value`=`reading.value`, `confidence`=`reading.confidence`; `None`→`null` (preserves "not trained") |
-| `heartbeat: Option<…>` | `heart_bpm: {…}\|null` | rename `heartbeat`→`heart_bpm` |
-| `presence/posture/restlessness` | same names `{value,confidence}\|null` | `posture.value`=`reading.label` (class), else numeric |
-| `anomaly: Option<…>` | `anomaly: {value,confidence,threshold}` | inject `threshold`=`MixtureOfSpecialists.veto_threshold` (0.5) |
-| `vetoed` / `stale` | `vetoed` / `stale` | pass through (drives the §4.5/§6 banners) |
-| *(absent)* | `room_id`, `seeds[]` | injected by the gateway from the **room registry** |
-
-A **room registry** (config or derived from `GET /api/cal/v1/calibration/baselines`) maps each `room_id` → bank name + serving SEED ids, so `GET /api/homecore/rooms` returns one adapted record per room. `Option::None` → JSON `null` keeps the null-vs-withheld distinction (§6 invariant 3) intact end-to-end.
-
-### 11.4 SEED registry & device-API proxy
-
-The gateway holds a **SEED registry** (`device_id` → base URL + bearer token + zone), populated by pairing (§4.10) and persisted server-side. `GET /api/homecore/seeds[/:id]` fans out to each SEED's on-device API and shapes the result to the §4.2 card/detail model. Expected SEED-side endpoints (the contract the SEED firmware must satisfy — a subset of its 98 endpoints): health; vector-store stats (`vector_count`, `dim`, `epoch`, `knn_latency_ms`, ingest rate); witness (`len`, `last_verify`, `valid`) + `POST verify`; onboard sensors (BME280/PIR/reed/ADS1115/vibration); reflex rules + thresholds; cognitive analysis (fragility, coherence phases); ingest feeders (ESP32 node ids + packet type `0xC5110003`/`0xC5110002` + rate). Offline/unreachable SEEDs surface as `online:false` (drives the §4.1 red tint) rather than failing the whole list.
-
-### 11.5 Appliance metrics collector (§4.1)
-
-`GET /api/homecore/appliance`, implemented in the gateway: CPU/RAM/uptime from `/proc`; Hailo load + temperature from the Hailo runtime/sysfs (or `ruvector-hailo-worker` stats); service health by probing `ruview-mcp-brain:9876`, `cognitum-rvf-agent:9004`, `ruvector-hailo-worker:50051`; event-bus rate from the `homecore` broadcast channel + its lag counter (already exposed for §4.1/§4.4).
-
-### 11.6 COG supervisor (§4.6)
-
-`GET /api/homecore/cogs`: read each `/var/lib/cognitum/apps/*/manifest.json` ([ADR-100](ADR-100-cog-packaging-specification.md)), the pid file, and verify `binary_sha256` + `binary_signature` (Ed25519) → status/shield. `POST …/cogs/:id/{start,stop,restart}` performs supervised process control; `GET …/cogs/:id/logs` tails `output.log`/`error.log`; `GET/PUT …/cogs/:id/config` reads/writes `config.json`. Hailo-arch COGs join the §11.5 Hailo stats. The Cog Store/App-Registry **browsing** panel was removed per product decision; this is operational management only.
-
-### 11.7 Witness aggregation + privacy (§4.9)
-
-`GET /api/homecore/witness` merges two chains chronologically: the `homecore` Ed25519 state-transition chain (exposed by a small `homecore-api` route over its witness log) and each paired SEED's SHA-256 ingest chain (proxied via the registry), paginated server-side. `GET/POST /api/homecore/privacy` reads/sets per-SEED privacy mode via the SEED privacy control plane ([ADR-141](ADR-141-bfld-privacy-control-plane-modes-attestation.md)) — the POST is the high-stakes confirmed toggle (§4.9). `GET /api/homecore/witness/export` packages both chains into the downloadable attestation bundle.
-
-### 11.8 Event history + automation CRUD (§4.8)
-
-`homecore-api` adds `GET /api/events?since=…` backed by `homecore-recorder` ([ADR-132](ADR-132-homecore-recorder-history-semantic-search.md)) for history (live updates continue over the existing WS). The automation builder persists through `GET/POST/DELETE /api/homecore/automations`, a thin HTTP wrapper over the `homecore-automation` engine's register/list/remove ([ADR-129](ADR-129-homecore-automation-engine.md)). RuView-specific triggers (RoomState thresholds, SEED reflex events) map onto the engine's trigger types.
-
-### 11.9 Entity provenance convention (§4.4/§6)
-
-The first-class provenance badge requires each entity to carry its lineage. Convention: every integration writes `attributes.source` (and, where known, `attributes.seed` / `attributes.cog`) when it sets state; `cog-ha-matter` ([ADR-116](ADR-116-cog-ha-matter-seed.md)) populates these from the ESP32 node → SEED → COG path and HA `via_device`. The gateway/UI resolves node→seed→cog from these attributes (no fabrication; missing lineage renders as "unknown", not invented).
-
-### 11.10 Auth, credentials, config
-
- **Browser → gateway:** one long-lived access token (the §4.10 LLAT), sent as `Authorization: Bearer`; validated by `homecore-api`'s `LongLivedTokenStore`. The dev default (`allow_any_non_empty`) stays for local runs; production provisions `HOMECORE_TOKENS`.
- **Gateway → upstreams:** SEED bearer tokens and the calibration token live **only** server-side (SEED registry + `HOMECORE_CALIBRATION_TOKEN`); never sent to the browser. This is the reason the gateway exists.
- **Config:** `HOMECORE_CALIBRATION_URL`, SEED registry store path, per-proxy timeout (default 2 s), `HOMECORE_UI_DEMO` (dev fixture). No browser CORS needed (same origin); gateway→upstream is server-to-server.
-
-### 11.11 Front-end changes
-
-`api.js`: drop the mock fallback from the production path — methods call the §11.2 gateway routes; `this.base` stays same-origin; the mock layer is reachable only under `?demo=1`/`HOMECORE_UI_DEMO`. Every panel renders a **typed empty/error state** (not mock) when its route returns `503/504`. `mock.js` moves to a dev fixture (kept for the offline test harness, excluded from the production bundle). The §10 frontend tests are re-pointed at the gateway contract (and gain contract tests per §11.2 route).
-
---
-
-## 12. Delivery plan to full functionality
-
-Staged so each wave is independently shippable behind the gateway, lands real data for a coherent set of panels, and has an explicit acceptance gate. "Class" reuses §11's tags.
-
-| Wave | Scope | Class | Acceptance gate |
-|---|---|---|---|
-| **W1 — Gateway foundation** | `/api/homecore/*` scaffold in `homecore-server`; auth passthrough; per-proxy timeout + typed errors; `api.js` base + remove prod mock (`?demo=1` only); panels get typed empty/error states | NEW-GW | Entities + live WS still green; with no upstreams, every other panel shows "upstream unavailable", **never** mock (unless `?demo=1`); Rust + JS suites pass |
-| **W2 — Rooms + Calibration** | `/api/cal/*` reverse-proxy; `GET /api/homecore/rooms` with the §11.3 RoomState adapter + room registry; wire §4.5 + the §4.7 wizard to real endpoints; delete the in-browser calibration stub | EXISTS (proxy+adapter) | Against a running `calibrate-serve` (replayed CSI), the wizard drives a real baseline→enroll→train→verify and §4.5 shows real `RoomState` with correct stale/veto/null mapping; contract test on the adapter |
-| **W3 — Events + Automations** | `GET /api/events` over `homecore-recorder`; `/api/homecore/automations` over `homecore-automation` | NEW-API | §4.8 history loads from recorder; an automation created in the UI persists and fires via the engine |
-| **W4 — COG management** | `/api/homecore/cogs*` supervisor over `/var/lib/cognitum/apps/` (manifest + pid + sig verify + logs + config) | NEW-GW | §4.6 lists real installed COGs; start/stop/restart works; sha256/signature shield reflects real verification; logs tail |
-| **W5 — SEED tier** | SEED registry + pairing; `/api/homecore/seeds*` device proxy; witness merge + privacy control; ESP32 provisioning | SEED-DEV | Against a real or emulated SEED API, §4.2/§4.3/§4.9/§4.10 show real vector-store/witness/sensor/reflex/cognition data; SEED tokens stay server-side; offline SEED → red tint, not a failed page |
-| **W6 — Appliance + federation + Hailo** | `/api/homecore/appliance` (host metrics + service probes); `/api/homecore/hailo`; `/api/homecore/federation` ([ADR-105](ADR-105-federated-csi-training.md)) | NEW-GW + APPLIANCE | §4.1 health is real; §4.6 Hailo HEF/throughput real; §4.3 federation round/coordinator/Krum real |
-
-**Definition of done (full functionality):** with W1–W6 merged and the upstream tiers running, loading `/homecore` with **no** `?demo=1` flag shows live data on all ten panels, `api.anyDemo()` is false, and no panel renders fabricated values. Panels whose tier is offline show typed empty/error states. The mock layer is reachable only as the `?demo=1` developer fixture.
-
-### 12.1 Wave status (this revision)
-
-| Wave | Status |
-|---|---|
-| **W1 — Gateway foundation** | ✅ DONE — `gateway.rs`, auth passthrough, typed `503/504`, merged into `build_app`; front-end mock removed from prod path + `?demo=1` fixture; typed error states. **Compiled + 12/12 Rust tests + JS suite green + run live.** |
-| **W2 — Rooms + Calibration** | ✅ DONE — `/api/cal/*` reverse-proxy + `GET /api/homecore/rooms` RoomState adapter; front-end calibration stub deleted (now proxies the real API). **Proven live against a calibration upstream** (proxy 200 + adapted shape); null-preservation unit-tested. |
-| **W3 — Events + Automations** | ⏳ gateway returns typed `503` (recorder/automation HTTP wrappers pending); front-end handles it gracefully (history note, builder still usable). |
-| **W4 — COG management** | ✅ supervisor DONE — lists `/var/lib/cognitum/apps/` manifests + pid liveness (returns `[]` live with no apps dir); start/stop/log/config control is the remaining follow-up. |
-| **W5 — SEED tier** | ⏳ gateway returns typed `503` (SEED registry + device proxy pending real/emulated SEED hardware). |
-| **W6 — Appliance + federation + Hailo** | ◑ appliance host metrics from `/proc` + port probes DONE (live `/proc` data verified); Hailo stats + federation remain `503` (need the accelerator stat source / coordinator). |
-
-**Status:** the gateway is **compiled and tested on Rust 1.89** (`cargo test -p homecore-server` = 12/12) and was **run live** (curl proof in §10). The one remaining caveat is intrinsic, not an environment limit: **W3/W5/W6-Hailo/federation depend on services/hardware that are not in this repo** (recorder/automation HTTP wrappers, real SEED nodes, the Hailo stat source), so they return honest typed `503`s and the UI shows error states — exactly as §2.2/§11.2 prescribe. W1/W2/W4/W6-appliance are functional now.
-
-### 12.2 Security review (PR #1082)
-
-A high-effort public-PR review of the merged gateway + front-end surfaced the following, all fixed and pinned by tests (`cargo test -p homecore-server` is now **18/18**):
-
-| # | Severity | Finding | Fix |
-|---|---|---|---|
-| 1 | **HIGH** | **Path-traversal / confused-deputy SSRF** in the `/api/cal/*` reverse-proxy. The wildcard path was interpolated into the upstream URL while `proxy()` attaches the privileged server-side calibration bearer, so `/api/cal/v1/../../x` (or `..%2f`, `%2e%2e`, leading `/`, `\`, double-encoded `%252e`) could escape the `…/api/` scope **with the token**. | `validate_proxy_path()` decode-then-checks and rejects absolute / backslash / dot-segment / encoded-traversal paths with a typed **400 before the URL is built** (GET **and** POST); legit `v1/...` paths still pass. |
-| 2 | Correctness | **CORS + tracing didn't cover gateway routes** — `/api/homecore/*` + `/api/cal/*` were `.merge()`d outside `homecore-api::router()`'s layers. | The audited HC-05 `build_cors_layer()` + `TraceLayer` are now applied to the whole merged app in `main.rs`. |
-| 3 | Honesty (§6) | **Fabricated data** — hardcoded `anomaly.threshold: 0.5` in the adapter; dashboard rendered `"null%"`/`"null°C"`; COG Hailo pill hardcoded `"connected"`; `rooms.js` defaulted a null threshold to `0.8`. | Threshold passes through the real upstream value or emits `null` (withheld); dashboard renders `—`; the Hailo pill reflects the real appliance probe; the UI treats a null threshold as withheld. |
-| 4 | Robustness | A string `hef` (forwarded verbatim) threw on `.forEach`/`.join`; `frames/target` could be `NaN%`/`Infinity%`; calibration Restart leaked the baseline `setTimeout` poll. | `asArray()` coercion; `target > 0` guard; cancellable poll cleared on Restart / panel teardown. |
-| 5 | Perf | Sequential per-bank RoomState fetches; blocking `std::net::TcpStream::connect_timeout` probes on an async handler; `mock.js` statically bundled. | Concurrent `futures::join_all`; async `tokio::net::TcpStream` + `timeout`; demo-only dynamic `import()` of `mock.js`. |
-
-**Known limitations carried forward (not regressions):**
- **`reqwest` rustls-only is a workspace-wide concern.** `homecore-server` opts into `rustls-tls` only, but cargo feature-unification means any sibling crate enabling the default `native-tls` re-introduces OpenSSL into the final binary. A true "no OpenSSL on the appliance" guarantee requires aligning **every** reqwest-pulling crate on rustls-only — out of scope for this PR; documented at the dependency in `Cargo.toml`.
- **DEV-mode auth.** When `HOMECORE_TOKENS` is unset, the token store falls back to `allow_any_non_empty()` (any non-empty bearer accepted) on `0.0.0.0`. This is pre-existing and intentionally **unchanged** here; the loud boot `warn!` is retained. Provision real tokens (`HOMECORE_TOKENS=…`) before exposing the server to a network.
@@ -1,166 +0,0 @@
-# ADR-132: HOMECORE-RECORDER — State History + Semantic Search
-
-| Field | Value |
-|-------|-------|
-| **Status** | Accepted |
-| **Date** | 2026-05-25 |
-| **Deciders** | ruv |
-| **Codename** | **HOMECORE-RECORDER** |
-| **Crate** | `v2/crates/homecore-recorder` |
-| **Relates to** | [ADR-126](ADR-126-ruview-native-ha-port-master.md) (HOMECORE master — series map row ADR-132), [ADR-127](ADR-127-homecore-state-machine-rust.md) (HOMECORE-CORE state machine), [ADR-124](ADR-124-rvagent-mcp-ruvector-npm-integration.md) (ruvector/SENSE-BRIDGE), [ADR-130](ADR-130-homecore-rest-websocket-api.md) (HOMECORE-API query surface, downstream) |
-| **Tracking issue** | [#800](https://github.com/ruvnet/RuView/pull/800) (HOMECORE intake) |
-
-> **Documented retroactively (2026-06-12).** The `homecore-recorder` crate shipped under
-> the ADR-126 series map (which planned an "ADR-132 HOMECORE-RECORDER") but the standalone
-> ADR file was never written; the crate's `Cargo.toml`, `README.md`, `lib.rs`, `schema.rs`,
-> and `semantic.rs` all cite "ADR-132". This ADR reverse-documents the decision that the
-> shipped, tested code already embodies (ADR-164 Gap G3 / Coverage-Gaps Lens §A). It does
-> **not** introduce new design; it records what is built. Date reflects the crate's intake
-> era (first commit `e96ebaea8`, 2026-05-25); real-impl pass landed in `7c8071145`
-> (2026-06-11).
-
---
-
-## 1. Context
-
-ADR-126 (the HOMECORE master) decided to reimplement Home Assistant (HA) natively in Rust.
-HA persists every state change to a SQLite *recorder* database; downstream features
-(history graphs, the logbook, long-term statistics, automation conditions that reference
-past state) all read that store. HOMECORE therefore needs a durable state-history backbone.
-
-Two forces shape the decision:
-
-1. **Migration / coexistence.** Users adopting HOMECORE will have an existing HA
-   `recorder` database. Reusing HA's on-disk schema (rather than inventing a new one) lets
-   HOMECORE read an existing HA `home-assistant_v2.db` directly and lets HA-aware tooling
-   read HOMECORE's store. This is the same trust boundary that `homecore-migrate`
-   (ADR-165) handles for `.storage/*.json`.
-2. **Semantic queries.** HA history is queried with SQL `BETWEEN`/`WHERE` clauses. The
-   HOMECORE platform already carries ruvector (ADR-124) for vector search, so the recorder
-   can additionally embed state changes and answer natural-language queries
-   ("which kitchen devices were warm at 3 PM?") via k-NN — a capability HA does not have.
-
-The recorder is the **durable-state surface**: if it is wrong, history, logbook, and
-historical-condition automations are all wrong. ADR-164 flagged it as a CRITICAL coverage
-gap precisely because such a load-bearing crate had no governing ADR.
-
-## 2. Decision
-
-Ship `homecore-recorder` as a SQLite state-history recorder with an HA-compatible schema
-and an optional ruvector-backed semantic index, in three phases. P1 and P2 are built and
-tested; P3 is planned.
-
-### 2.1 Storage — SQLite with the HA recorder schema (P1, shipped)
-
- Persist via `sqlx` with the SQLite backend only (no Postgres, no TLS feature set).
- Mirror HA recorder **schema v48** so the store is bidirectionally readable
-  (`src/schema.rs`):
-  - `state_attributes` — shared attribute JSON blobs, deduped by an FNV-1a 64-bit hash
-    stored as a signed `i64` (matches HA's dedup key);
-  - `states` — one row per state write (`entity_id`, `state`, `attributes_id` FK,
-    `last_changed_ts`/`last_updated_ts` as REAL Unix seconds, `context_id` UUID);
-  - `events` — domain events (`event_type`, `event_data` JSON, `time_fired_ts`);
-  - `recorder_runs` — boot/shutdown bookends for history-gap detection.
- All DDL uses `CREATE TABLE IF NOT EXISTS`, so schema application is idempotent and safe
-  on every startup.
- Default persistence path `.homecore/home.db` (configurable).
-
-### 2.2 Capture — listener on the HOMECORE event bus (P1, shipped)
-
- `RecorderListener` subscribes to the HOMECORE event bus (ADR-127) and captures
-  `StateChanged` events, writing snapshots through `Recorder` (`src/listener.rs`,
-  `src/db.rs`).
- A `DedupEngine` (`src/dedup.rs`) skips redundant writes when the state hash is unchanged,
-  matching HA's stateful-listener behaviour.
-
-### 2.3 Semantic search — ruvector HNSW (P2, shipped, feature-gated)
-
- Behind the `ruvector` Cargo feature, the `Recorder` additionally calls a `SemanticIndex`
-  implementation (`src/semantic.rs`) that embeds state attributes and stores vectors in a
-  `ruvector-core` HNSW index for k-NN search.
- P2 embeddings are **hash-based** (sha2) — a deliberate, honest placeholder. They give a
-  working HNSW surface without claiming sentence-level semantic quality.
- When the feature is off, `NullSemanticIndex` satisfies the `SemanticIndex` trait bound
-  with no allocation, so the structural recorder ships independently of ruvector.
-
-### 2.4 Real sentence embeddings (P3, planned — not yet built)
-
- Replace the hash embeddings with ruvector-attention sentence embeddings (dim → 384). Not
-  implemented; tracked as a follow-up. The README and `Cargo.toml` label this P3 explicitly.
-
-### 2.5 Test evidence (as shipped)
-
- P1: 14 tests (`cargo test -p homecore-recorder --no-default-features`).
- P2: 20 tests (`cargo test -p homecore-recorder --features ruvector`).
-
-## 3. Consequences
-
-**Positive.**
-
- HA-schema compatibility makes migration (ADR-165) and coexistence cheap: HOMECORE can
-  read an existing HA `recorder.db`, and any SQLite tool can read HOMECORE's history.
- The semantic index is **additive** and feature-gated: the durable structural recorder has
-  no hard dependency on ruvector, so the storage backbone ships first.
- Standard SQLite means no proprietary export format; history is directly queryable.
-
-**Negative / honest limits.**
-
- P2 semantic search uses **hash embeddings**, not real sentence embeddings — query quality
-  is limited until P3. This is disclosed in the crate docs and here; it must not be cited as
-  semantic-quality-validated.
- No per-crate benchmarks exist yet; the latency figures in the README
-  (state-write p50 < 2 ms, semantic search < 10 ms on 1 M records) are design targets /
-  estimates, **needs verification** with a criterion baseline.
- Pinning to HA schema v48 couples HOMECORE to a specific HA recorder schema generation;
-  future HA schema bumps require an explicit migration step.
-
-**Neutral.**
-
- This ADR governs the recorder crate only. The query/REST surface over recorder data is
-  HOMECORE-API (ADR-130, P3); automation conditions on historical state are
-  HOMECORE-automation (ADR-129, P3).
-
-## 3a. Security review (2026-06, post-ADR-154–159 sweep)
-
-A beyond-SOTA security review of `homecore-recorder` covered SQL injection, retention/purge
-correctness, fail-closed write integrity, semantic-store NaN poisoning, and PII exposure.
-
-**Confirmed clean (with evidence):**
-
- **SQL injection — clean.** Every query in `db.rs` uses bound `?` parameters; no user- or
-  entity-influenceable value is interpolated into SQL via `format!`/concatenation. The only
-  `format!` builds the `LIKE` *pattern* string, which is itself **bound** as a parameter with
-  `ESCAPE '\\'` and `% _ \` escaping — so a metacharacter payload is matched literally. Pinned
-  by `malicious_entity_id_is_stored_literally_not_executed` (a `'; DROP TABLE states; --` state
-  value leaves the table intact and round-trips verbatim) and
-  `like_metacharacters_in_query_are_literal_not_wildcards`.
- **NaN-index poisoning — structurally impossible.** Embeddings are SHA-256 → `i32` →
-  `f32`; an `i32`→`f32` cast is always finite (never NaN/Inf), and an all-zero-digest is
-  guarded by the `norm > 1e-10` check. Empty-index search, empty-string query, and `k=0` were
-  probed and all return `Ok(0)` with no panic. (Unlike the calibration/vitals/geo paths, no raw
-  sensor float ever reaches the index.)
- **Fail-closed writes.** A removal event returns `Ok(None)`; semantic-index failure is logged,
-  not propagated, so it never blocks the durable SQLite write; `EntityId` parse failure falls
-  back to a sentinel rather than panicking.
-
-**Fixed (real bounding bugs):**
-
- **Memory-DoS — `get_state_history` was unbounded.** No `LIMIT`, so a wide time window over a
-  high-frequency entity loaded an unbounded row set into memory. Now capped at
-  `MAX_HISTORY_ROWS` (1,000,000); sibling search paths were already `k`-bounded.
- **Disk-DoS / documented-but-missing `purge`.** The README advertised `Recorder::purge`, but
-  no retention path existed → unbounded disk growth. Added a **transactional** `purge(older_than)`
-  with an **exclusive** cutoff (idempotent, no off-by-one) that deletes old `states`/`events` and
-  GCs orphaned `state_attributes` blobs (dedup-shared blobs kept until their last referrer is gone).
-
-`homecore-recorder` tests: 19 → 25 (`--no-default-features`) / 25 → 31 (`--features ruvector`),
-0 failed. Python deterministic proof unchanged (recorder is off the signal proof path).
-
-## 4. Links
-
- Crate: `v2/crates/homecore-recorder/` — `Cargo.toml`, `README.md`, `src/lib.rs`,
-  `src/db.rs`, `src/schema.rs`, `src/dedup.rs`, `src/listener.rs`, `src/semantic.rs`.
- [ADR-126](ADR-126-ruview-native-ha-port-master.md) — HOMECORE master (series map: ADR-132 = HOMECORE-RECORDER).
- [ADR-165](ADR-165-homecore-migrate-from-home-assistant.md) — HOMECORE-MIGRATE (reads HA `.storage`; P2 exports a side-by-side recorder DB).
- [ADR-164](ADR-164-adr-corpus-gap-analysis.md) — gap analysis that surfaced this missing ADR (Gap G3).
- [Home Assistant Recorder integration](https://www.home-assistant.io/integrations/recorder/).
@@ -174,71 +174,3 @@ vs. an in-memory array at compile time), which intersects with ADR-084 (RabitQ)
 | **P1** (this ADR) | `intent`, `recognizer` (regex), `handler` (5 built-ins), `runner` (trait + noop), `pipeline` (end-to-end wiring), 10–15 tests |
 | **P2** | Real `tokio::process::Child` runner with Windows-safe teardown; `SemanticIntentRecognizer` with ruvector HNSW |
 | **P3** | STT/TTS bridge, satellite protocol, cloud fallback |
-
---
-
-## 6. Security review (beyond-SOTA, untrusted-input → action path)
-
-A focused security review of the Assist pipeline — `utterance → recognizer →
-intent → handler → action`, plus `RufloRunner` — treating the utterance as
-untrusted input (voice transcripts, the WebSocket `assist` command). This
-surface was not covered by the ADR-154–159 sweep.
-
-### 6.1 Finding fixed — HC-ASSIST-01 (unbounded-utterance DoS, LOW)
-
-Both `RegexIntentRecognizer::recognize` and the semantic `recognize_scored`
-accepted utterances of **unbounded length** and ran `to_lowercase()` (a full
-clone) + a per-registered-pattern scan (and, in the semantic path, full
-tokenisation + feature-hash embedding) before any bound — an allocation/CPU
-amplification on attacker-controlled input. The `regex` crate is **linear-time**
-(RE2-style finite automaton, no catastrophic backtracking), so this was a
-throughput/memory DoS, not a hang.
-
-**Fix:** `MAX_UTTERANCE_BYTES = 4096` (far above any real spoken command),
-checked at **both** recognizer boundaries *before* any allocation/scan. An
-over-length utterance **fails closed** to `Ok(None)` — no intent, no action,
-identical to an unrecognised phrase — so it can never be coerced into firing a
-handler. Pinned by `over_length_utterance_fails_closed` (an over-length
-utterance that *contains* a valid command resolves to `None`, which would have
-matched on the old code) and `over_length_utterance_fails_closed_semantic`.
-
-### 6.2 Dimensions confirmed clean (with evidence)
-
- **Command / argument injection — NO SUBPROCESS SURFACE.** The `RufloRunner`
-  has exactly two impls: `NoopRunner` (no process) and `LocalRunner` (runs the
-  local recognizer, no process). There is **no** `std::process` / `tokio::process`
-  / `Command` / process `.spawn()` anywhere in the crate — the trait `spawn` is
-  only a `started: bool` lifecycle flag — and `RufloRunnerOpts.{script_path,env}`
-  are **inert data, never consumed**. The live `node ruflo-agent.js` runner is
-  genuinely data-gated/future (P2). Defence-in-depth: the `entity_id` capture
-  class `[a-z_][a-z0-9_ .]*` **excludes every shell/SQL metacharacter**, so even
-  when an injection-shaped utterance resolves (the regex is not exact-anchored),
-  the captured slot is a clean token — sanitisation by construction. Pins:
-  `shell_metachars_never_survive_into_a_resolved_slot`,
-  `runner_opts_are_inert_no_process_spawned`,
-  `pipeline_injection_shaped_utterance_carries_no_metachars_to_service`.
- **ReDoS — STRUCTURALLY IMPOSSIBLE.** `regex 1.12.3` (no `fancy-regex` in the
-  dependency tree) is linear-time; a classic `(a+)+$` shape on adversarial input
-  completes in bounded time. Pin:
-  `pathological_backtracking_pattern_completes_in_bounded_time`. Patterns are
-  operator-registered, not user-supplied, in any case.
- **NaN-poisoning — EMBEDDINGS STRUCTURALLY FINITE.** The embedding path takes
-  only `&str` and produces values via FNV feature-hashing + a guarded L2
-  normalise (`norm > 1e-12`); no external float input, no unguarded division, so
-  a crafted utterance cannot inject NaN/Inf to poison the cosine k-NN. Cosine
-  against the zero vector is a finite `0.0`; an empty index `max_by` returns
-  `None` (no panic); the NaN-safe `partial_cmp().unwrap_or(Equal)` is already in
-  place. Pins: `embeddings_are_structurally_finite`,
-  `cosine_with_zero_vector_is_finite_not_nan`,
-  `empty_utterance_against_empty_index_no_panic_no_match`.
- **Intent confusion / fail-closed.** An unrecognised utterance → `not_understood()`
-  (no service call); a recognised intent with no registered handler →
-  `not_understood()`; semantic below-threshold / empty-index → regex fallback.
-  No default high-privilege intent, no fail-open path.
- **Panic-on-input.** No `unwrap`/`expect`/index reachable from a crafted
-  utterance; the one `exemplars[id]` index uses an `id` from `enumerate()` over
-  the append-only exemplar `Vec` (no remove API), so it is always in bounds.
-
-`cargo test -p homecore-assist --no-default-features`: **29→36, 0 failed** (+7);
-default/`semantic`: **39→48, 0 failed** (+9). Python deterministic proof
-unchanged (homecore-assist is off the signal proof path).
@@ -2,7 +2,7 @@

 | Field | Value |
 |-------|-------|
-| **Status** | Accepted — partial (built + tested building block; integration glue pending — see §8 Implementation Status, commit `11f89727f`) |
+| **Status** | Proposed |
 | **Date** | 2026-05-28 |
 | **Deciders** | ruv |
 | **Codebase target** | `wifi-densepose-core` (`types.rs`: `CsiFrame`/`CsiMetadata`); `wifi-densepose-signal/src/ruvsense/mod.rs` (`RuvSensePipeline`, six-stage flow); `v2/Cargo.toml` (workspace topology) |
--- a/Show More
+++ b/Show More
				`@@ -1 +0,0 @@`
				`9c35e541d51f00998691b98948887ebca09b907d8eb29a113f97e792340456ba`
				`@@ -1 +0,0 @@`
				{"frames": [{"pred": [[0.4003, 0.2734], [0.5038, 0.4197], [0.2053, 0.4438], [0.4397, 0.685], [0.5796, 0.7645], [0.8001, 0.2195], [0.2789, 0.2833], [0.314, 0.5439], [0.511, 0.2259], [0.6008, 0.46], [0.4837, 0.3879], [0.3475, 0.5597], [0.6569, 0.3575], [0.437, 0.6539], [0.2341, 0.6038], [0.7331, 0.392], [0.5615, 0.4915]]}, {"pred": [[0.4669, 0.6066], [0.6012, 0.7873], [0.4124, 0.5997], [0.2832, 0.281], [0.2732, 0.3635], [0.2503, 0.4848], [0.6827, 0.715], [0.4336, 0.7165], [0.295, 0.3386], [0.5337, 0.3544], [0.4397, 0.5474], [0.5163, 0.5528], [0.7547, 0.6799], [0.4195, 0.4448], [0.2257, 0.2269], [0.384, 0.2176], [0.2419, 0.4332]]}, {"pred": [[0.5585, 0.283], [0.4325, 0.2934], [0.463, 0.4744], [0.4188, 0.3454], [0.215, 0.7565], [0.527, 0.2353], [0.7084, 0.6124], [0.3015, 0.6744], [0.4103, 0.3532], [0.7243, 0.6932], [0.3302, 0.4918], [0.2072, 0.3754], [0.7914, 0.4878], [0.7618, 0.4079], [0.323, 0.3386], [0.7104, 0.4997], [0.2673, 0.6077]]}, {"pred": [[0.6372, 0.4984], [0.4184, 0.6763], [0.4498, 0.7549], [0.2924, 0.303], [0.3069, 0.7022], [0.3954, 0.5098], [0.7836, 0.6071], [0.4733, 0.7114], [0.3407, 0.3793], [0.3408, 0.4678], [0.4156, 0.4911], [0.4525, 0.7519], [0.5117, 0.1985], [0.1893, 0.6784], [0.6281, 0.5346], [0.5175, 0.673], [0.36, 0.3665]]}, {"pred": [[0.5535, 0.6537], [0.568, 0.511], [0.4705, 0.5377], [0.6372, 0.7163], [0.5493, 0.7515], [0.2559, 0.4549], [0.2553, 0.6176], [0.2991, 0.6154], [0.7185, 0.7986], [0.4586, 0.5057], [0.2975, 0.4525], [0.3263, 0.3719], [0.5131, 0.4576], [0.557, 0.5268], [0.6572, 0.7736], [0.2146, 0.6526], [0.4662, 0.7371]]}, {"pred": [[0.2924, 0.7595], [0.2612, 0.2315], [0.2488, 0.7751], [0.2329, 0.7282], [0.4744, 0.4206], [0.3618, 0.267], [0.2477, 0.285], [0.3976, 0.3746], [0.494, 0.2874], [0.3596, 0.2112], [0.3311, 0.4692], [0.6912, 0.4727], [0.4434, 0.5233], [0.4139, 0.7048], [0.425, 0.3937], [0.2326, 0.631], [0.2655, 0.7116]]}, {"pred": [[0.3609, 0.3437], [0.285, 0.486], [0.7734, 0.5468], [0.3657, 0.4093], [0.4728, 0.5019], [0.1866, 0.3545], [0.2172, 0.2028], [0.5613, 0.5238], [0.6252, 0.7205], [0.7998, 0.2954], [0.242, 0.7063], [0.6259, 0.6883], [0.5148, 0.7141], [0.5577, 0.7434], [0.3233, 0.2131], [0.2652, 0.7066], [0.5753, 0.5885]]}, {"pred": [[0.6787, 0.6504], [0.6051, 0.2297], [0.2539, 0.3475], [0.6437, 0.7807], [0.4981, 0.6149], [0.5716, 0.2367], [0.6486, 0.3632], [0.2433, 0.369], [0.6061, 0.3731], [0.4955, 0.2591], [0.7676, 0.7602], [0.6899, 0.7716], [0.3143, 0.7707], [0.3031, 0.4997], [0.7076, 0.5133], [0.3382, 0.7196], [0.2002, 0.4871]]}]}
				`@@ -1 +0,0 @@`
				{"frames": [{"gt": [[0.3943, 0.2905], [0.5215, 0.4194], [0.2225, 0.4602], [0.4547, 0.6961], [0.5765, 0.7686], [0.7858, 0.2279], [0.2866, 0.2707], [0.3084, 0.549], [0.5286, 0.2377], [0.6082, 0.4566], [0.4719, 0.3799], [0.3465, 0.5447], [0.6377, 0.3728], [0.4509, 0.6543], [0.2235, 0.6009], [0.7253, 0.3882], [0.5479, 0.4737]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.4845, 0.5985], [0.5883, 0.7959], [0.4315, 0.6012], [0.3008, 0.2703], [0.2776, 0.3486], [0.2483, 0.4695], [0.6916, 0.7184], [0.4153, 0.7305], [0.3057, 0.3392], [0.5535, 0.3576], [0.4216, 0.5398], [0.5093, 0.5706], [0.7397, 0.668], [0.4354, 0.4394], [0.2373, 0.2404], [0.404, 0.2315], [0.2609, 0.4182]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.5684, 0.2891], [0.4185, 0.2737], [0.4796, 0.4903], [0.4056, 0.3589], [0.2139, 0.7706], [0.5259, 0.2162], [0.718, 0.6177], [0.3002, 0.6632], [0.3978, 0.3338], [0.7116, 0.6836], [0.336, 0.5106], [0.2168, 0.3677], [0.7739, 0.4683], [0.773, 0.4188], [0.318, 0.3226], [0.7043, 0.4877], [0.2509, 0.5964]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.6501, 0.4868], [0.3995, 0.6805], [0.4408, 0.7681], [0.2762, 0.2907], [0.2877, 0.6959], [0.4102, 0.5292], [0.7825, 0.5898], [0.4603, 0.723], [0.3511, 0.3758], [0.3556, 0.4514], [0.4123, 0.4749], [0.4524, 0.7506], [0.5141, 0.2112], [0.2024, 0.6795], [0.6351, 0.5339], [0.5333, 0.6706], [0.3491, 0.3662]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.537, 0.656], [0.5675, 0.5033], [0.4714, 0.52], [0.6195, 0.7259], [0.5357, 0.766], [0.273, 0.4653], [0.2439, 0.6017], [0.2927, 0.6297], [0.7297, 0.7805], [0.439, 0.4924], [0.2969, 0.4589], [0.3174, 0.3911], [0.5324, 0.4643], [0.5744, 0.5074], [0.673, 0.783], [0.2238, 0.6674], [0.4534, 0.7468]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.2896, 0.7515], [0.2537, 0.2345], [0.2434, 0.763], [0.2502, 0.7137], [0.4723, 0.4035], [0.3607, 0.2775], [0.2657, 0.2969], [0.3872, 0.383], [0.5001, 0.3067], [0.3503, 0.2092], [0.3137, 0.4849], [0.6914, 0.4593], [0.4359, 0.504], [0.4056, 0.6994], [0.4428, 0.4085], [0.2424, 0.6445], [0.2507, 0.7048]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.3692, 0.3453], [0.2945, 0.4675], [0.7836, 0.5282], [0.3857, 0.414], [0.4848, 0.5017], [0.203, 0.3585], [0.225, 0.2135], [0.5513, 0.5175], [0.6296, 0.7275], [0.7908, 0.2897], [0.2263, 0.7012], [0.6403, 0.6873], [0.5026, 0.701], [0.5504, 0.7357], [0.338, 0.2187], [0.2629, 0.7015], [0.5757, 0.6084]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}, {"gt": [[0.6786, 0.649], [0.5956, 0.2396], [0.2447, 0.3593], [0.6439, 0.7854], [0.4874, 0.6102], [0.5857, 0.2465], [0.6459, 0.3827], [0.2364, 0.3613], [0.6054, 0.3745], [0.4798, 0.2711], [0.7869, 0.7618], [0.6919, 0.7809], [0.3259, 0.7674], [0.285, 0.5144], [0.6921, 0.5052], [0.3388, 0.7386], [0.2022, 0.495]], "vis": [1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], "scale": 1.0}]}