frank/ruvnet--RuView
1
0
Fork 0
mirror of https://github.com/ruvnet/RuView synced 2026-08-02 19:11:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(docs): correct unsubstantiated 92.9% PCK@20 camera-supervised claim (#535)

Browse Source 
The README claimed "92.9% PCK@20" for camera-supervised pose training. That
figure appears nowhere in ADR-079 (the source ADR) and is ~2.6x the ADR's own
success target (">35% PCK@20"). ADR-079 phases P7 (data collection), P8
(training + evaluation on real paired data) and P9 (cross-room LoRA) are all
still `Pending`, so no measured camera-supervised PCK@20 has been published.

- README: replace the two "92.9% PCK@20" claims with the proxy-supervised
  baseline (~2.5%) and the ADR-079 target (35%+), noting the eval phases are
  pending.
- CHANGELOG: add an Unreleased entry.

Surfaced by the PowerPlatePulse training-pipeline audit (2026-05-11). Six other
audit findings (vitals features absent from training; wifi-densepose-signal
ghost dep; PIR/BME280 in MODEL_CARD unimplemented; proof.rs uses
SyntheticCsiDataset only; 56-subcarrier/1-NIC default; multi-band 168-subcarrier
mesh not in training config) are listed in the PR body for follow-up.
This commit is contained in:
rUv
2026-05-11 23:40:52 -04:00
committed by GitHub
parent df9d3b0eea
commit bd4f81749a
2 changed files with 13 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -9,7 +9,7 @@
> **Beta Software** — Under active development. APIs and firmware may change. Known limitations:
> - ESP32-C3 and original ESP32 are not supported (single-core, insufficient for CSI DSP)
> - Single ESP32 deployments have limited spatial resolution — use 2+ nodes or add a [Cognitum Seed](https://cognitum.one) for best results
> - Camera-free pose accuracy is limited — use [camera ground-truth training](docs/adr/ADR-079-camera-ground-truth-training.md) for 92.9% PCK@20
> - Camera-free pose accuracy is limited (PCK@20 ≈ 2.5% with proxy labels) — [camera ground-truth training](docs/adr/ADR-079-camera-ground-truth-training.md) targets **35%+ PCK@20**; the pipeline is implemented, but the data-collection and evaluation phases (ADR-079 P7–P9) are still pending, so no measured camera-supervised PCK@20 has been published yet
>
> Contributions and bug reports welcome at [Issues](https://github.com/ruvnet/RuView/issues).
@@ -56,7 +56,7 @@ RuView also supports pose estimation (17 COCO keypoints via the WiFlow architect
> | 🧱 **Through-wall** | Fresnel zone geometry + multipath modeling | Up to 5m depth |
> | 🧠 **Edge intelligence** | 8-dim feature vectors + RVF store on Cognitum Seed | $140 total BOM |
> | 🎯 **Camera-free training** | 10 sensor signals, no labels needed | 84s on M4 Pro |
> | 📷 **Camera-supervised training** | MediaPipe + ESP32 CSI → 92.9% PCK@20 | 19 min on laptop |
> | 📷 **Camera-supervised training** | MediaPipe + ESP32 CSI → **35%+ PCK@20 target** (ADR-079; eval phases pending) | ~19 min on laptop (pipeline) |
> | 📡 **Multi-frequency mesh** | Channel hopping across 6 bands, neighbor APs as illuminators | 3x sensing bandwidth |
> | 🌐 **3D point cloud** *(optional fusion)* | Camera depth (MiDaS) + WiFi CSI + mmWave radar → unified spatial model | 22 ms pipeline · 19K+ points/frame |