frank/ruvnet--RuView
1
0
Fork 0
mirror of https://github.com/ruvnet/RuView synced 2026-08-09 20:21:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(train): falsifiable occupancy benchmark with anti-overfitting gate

Browse Source 
Makes the presence/person-count "beyond SOTA" claim falsifiable in code
instead of aspirational (the unfalsifiability gap from the beyond-SOTA system
review). occupancy_bench grades predictions vs ground truth and gates a SOTA
claim behind one claim_allowed invariant requiring ALL of:

- DataProvenance::Measured — synthetic/mock data is scorable for regression
  but never claimable (anti-mock-contamination; the CLAUDE.md Kconfig-bug
  lesson made structural).
- A leak-free EvalSplit — validate() refuses any split where a subject OR
  environment id appears in both train and test (subject leakage /
  per-environment overfitting).
- n_test >= min_test_samples (small-N guard).
- Presence F1 whose bootstrap-CI lower bound (deterministic seeded splitmix64)
  clears the threshold — not the point estimate.
- Count MAE within threshold.

The claim string is unreadable except through the gate (NO_CLAIM otherwise),
same discipline as the ruview-gamma acceptance gate. What remains is data, not
method: a frozen, SHA-pinned, subject/environment-disjoint measured replay set
turns the claim into a passing/failing test.

Lives in wifi-densepose-train (the eval bounded context, alongside ablation/
eval/metrics). 10 tests cover each refusal path; warning-clean under the
crate's missing_docs lint. Workspace gate 2,914 passed / 0 failed. Doc 03
updated.

https://claude.ai/code/session_01MjBucx95K4BuUxZi8NWwRH
This commit is contained in:
Claude
2026-06-10 20:43:42 +00:00
parent a8291d2535
commit d925538773
4 changed files with 577 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+1
View File
@@ -21,6 +21,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- **RF tomography solver hoisting** — ISTA gradient buffer no longer allocated inside the 100-iteration loop, and the Frobenius Lipschitz bound moved from per-`reconstruct` to construction (`ruvsense/tomography.rs`). Bit-identical results.
### Added
- **Falsifiable occupancy benchmark (`wifi-densepose-train::occupancy_bench`).** Makes the presence/person-count "beyond SOTA" claim falsifiable in code instead of aspirational (the unfalsifiability gap from the beyond-SOTA system review). Grades predictions vs ground truth and gates a SOTA claim behind one `claim_allowed` invariant requiring all of: `DataProvenance::Measured` (synthetic/mock is scorable but **never claimable** — anti-mock-contamination per the CLAUDE.md Kconfig-bug lesson), a leak-free `EvalSplit` (refuses any split where a subject *or* environment id appears in both train and test — subject leakage / per-environment overfitting), `n_test ≥ min`, presence-F1 **bootstrap-CI lower bound** (deterministic seeded splitmix64) clearing the threshold, and count MAE within threshold. The claim string is unreadable except through the gate (`NO_CLAIM` otherwise) — same discipline as the `ruview-gamma` acceptance gate. What remains is data, not method: a frozen, SHA-pinned, subject/environment-disjoint measured replay set turns the claim into a passing/failing test. 10 tests cover each refusal path.
- **Live trust path: sensing-server now routes real frames through the governed `StreamingEngine`.** Previously the live server ran only the *bare* `MultistaticFuser` (fused amplitudes, no trust control plane), while the privacy/provenance/witness engine (ADR-135..146) ran only on synthetic in-test frames — the gap called out in ADR-136 §8 and the beyond-SOTA system review (the privacy control plane was bypassable). New `engine_bridge` module drives `StreamingEngine::process_cycle` from the server's live `NodeState` map (reusing the existing `NodeState → MultiBandCsiFrame` conversion), lazily wiring each node as a WorldGraph sensor and bounding belief growth via the retention cap. Wired additively into both live ESP32/WiFi fusion sites in `main.rs` (split-borrow off the write guard; does not alter person-count behavior) and stores the latest BLAKE3 witness on `AppState`. Every published belief now carries evidence + model + calibration + privacy decision and a deterministic witness. Adds `wifi-densepose-engine/-worldgraph/-bfld/-geo` deps. 6 new bridge tests (witnessed belief with provenance, determinism, idempotent node registration, retention bound, privacy-mode propagation); sensing-server suite 430+128 green.
### Fixed