frank/ruvnet--RuView
1
0
Fork 0
mirror of https://github.com/ruvnet/RuView synced 2026-07-24 17:43:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(changelog): record ADR-151 calibration API (calibrate-serve)

Browse Source 
Co-Authored-By: claude-flow <ruv@ruv.net>
This commit is contained in:
ruv
2026-06-09 11:48:59 -04:00
parent 181d971e64
commit 901f12add9
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+1
View File
@@ -19,6 +19,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- **`--export-rvf` no longer silently produces a placeholder model — PR #920.** The `--export-rvf` handler ran *before* `--train`/`--pretrain` and unconditionally wrote placeholder sine-wave weights, so the documented `--train … --export-rvf <path>` workflow short-circuited to a fake model and never trained (while printing "exported successfully"). It now emits the placeholder **container-format demo** only standalone (with a clear warning), and falls through to real training when `--train`/`--pretrain` is set; docs point to `--save-rvf` for the real model. 3 guard tests.
### Added
- **ADR-151 + `wifi-densepose calibrate-serve` — UI-drivable per-room calibration API.** ADR-151 specifies the room-first calibration & specialized-model-training pipeline (`baseline → enroll → extract → train` → a bank of small ruVector specialists distilled from the frozen HF RF Foundation Encoder, ADR-150). Ships Stage 1: a CORS-enabled Axum HTTP API around the ADR-135 `CalibrationRecorder` so a UI can drive an empty-room baseline capture from the ESP32 CSI stream — `POST /start`, `GET /status` (live progress), `POST /stop`, `GET /result`, `GET /baselines`, `GET /health`. A background task owns the UDP socket + recorder (lock-free); plus a firewall-free `scripts/csi-udp-relay.py` for local Windows ESP32 testing without admin. Validated end-to-end against live ESP32 raw CSI (`edge_tier=0`): start → 120 frames → finalized 52-subcarrier baseline. 19 CLI tests pass.
- **WiFi-CSI pose: efficiency frontier + per-room calibration service** (ADR-150 §3.2–3.6). Two beyond-SOTA results on the MM-Fi benchmark, plus the deployment mechanism that resolves real-world generalization:
- **Efficiency frontier** — a **75 K-param model beats published SOTA** (74.3% vs MultiFormer 72.25% torso-PCK@20); every config from `micro` up is Pareto-dominant (smaller *and* more accurate than prior work). Shipped a deployable **int4 edge model (~20 KB, verified 74.08%, 0.135 ms single-thread CPU)** — published at [`ruvnet/wifi-densepose-mmfi-pose/edge`](https://huggingface.co/ruvnet/wifi-densepose-mmfi-pose). See [`docs/benchmarks/wifi-pose-efficiency-frontier.md`](docs/benchmarks/wifi-pose-efficiency-frontier.md).
- **Generalization solved by few-shot calibration** — zero-shot cross-subject (~64%) and cross-environment (~10%) are *not* closeable by algorithms (CORAL, DANN, instance-norm, contrastive foundation-pretraining all tested, all failed) or by more training subjects (saturates ~64%). But **~100–200 labeled in-room samples recover SOTA-level pose**: cross-subject 64→76%, **cross-environment 10→73% (60% from just 5 samples)** — deployable as a **~11 KB per-room LoRA adapter** on a frozen shared base. Full empirical chain in ADR-150 §3.2–3.6.