berkus
/
wifi-densepose
mirror of https://github.com/ruvnet/wifi-densepose.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs(#882): complete the "100% presence" retraction across all docs (#916) 

The v1 "100% presence accuracy" headline was already retracted in the
README / user-guide intro / proof-of-capabilities — but 6 secondary
spots still flatly claimed "100% accuracy, never false alarms", which
made proof-of-capabilities.md's "replaced everywhere" assertion untrue.

Completed the retraction in-place with the honest label-free metric
(82.3% held-out temporal-triplet; v1 was a single-class recording where
a constant "yes" scores ~99.98%):

- docs/readme-details.md — 2 benchmark tables + the pre-trained-model row
- docs/user-guide.md — capability table, model-file comment, applications list
- CHANGELOG.md — annotated the historical entry in-place (kept as public
  record per built-in-public ethos, not rewritten)

Verified: no remaining flat "100% presence/accuracy" claim lacks a
retraction marker; proof-of-capabilities.md "replaced everywhere" is now
accurate.
This commit is contained in:
rUv 2026-06-02 18:50:39 +02:00 committed by GitHub
parent 88b835dd89
commit 91b0e625bd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@ -430,7 +430,7 @@ Model release (no new firmware binary). Firmware remains at v0.6.0-esp32.
- Security fix merged via PR #310. - Security fix merged via PR #310.
### Performance ### Performance
- Presence detection: 100% accuracy on 60,630 overnight samples. - Presence detection: 100% accuracy on 60,630 overnight samples. *(Retracted — that recording was single-class (one sleeping person, 6,062/6,063 frames "present"), so a constant "yes" scores ~99.98%. Superseded by the honest 82.3% held-out temporal-triplet metric; see [#882](https://github.com/ruvnet/RuView/issues/882). Kept here as the in-place public record.)*
- Inference: 0.008 ms per sample, 164K embeddings/sec. - Inference: 0.008 ms per sample, 164K embeddings/sec.
- Contrastive self-supervised training: 51.6% improvement over baseline. - Contrastive self-supervised training: 51.6% improvement over baseline.

6
docs/readme-details.md
View File

@ -122,7 +122,7 @@ node scripts/benchmark-ruvllm.js --model models/csi-ruvllm # benchmark
| What we measured | Result | Why it matters | | What we measured | Result | Why it matters |
|-----------------|--------|---------------| |-----------------|--------|---------------|
| **Presence detection** | **100% accuracy** | Never misses a person, never false alarms | | **CSI embedding quality** | **82.3% held-out temporal-triplet** | Honest label-free metric on the last 20% by time (v1's "100% presence" was a single-class recording — retracted, [#882](https://github.com/ruvnet/RuView/issues/882)) |
| **Inference speed** | **0.008 ms** per embedding | 125,000x faster than real-time | | **Inference speed** | **0.008 ms** per embedding | 125,000x faster than real-time |
| **Throughput** | **164,183 embeddings/sec** | One Mac Mini handles 1,600+ ESP32 nodes | | **Throughput** | **164,183 embeddings/sec** | One Mac Mini handles 1,600+ ESP32 nodes |
| **Contrastive learning** | **51.6% improvement** | Strong pattern learning from real overnight data | | **Contrastive learning** | **51.6% improvement** | Strong pattern learning from real overnight data |
@ -233,7 +233,7 @@ python firmware/esp32-csi-node/provision.py --port COM9 --hop-channels "1,6,11"
| **kNN similarity search** | "Find the 10 most similar states to right now" — anomaly detection, fingerprinting | Cognitum Seed | | **kNN similarity search** | "Find the 10 most similar states to right now" — anomaly detection, fingerprinting | Cognitum Seed |
| **Witness chain** | SHA-256 tamper-evident audit trail for every measurement (1,747 entries validated) | Cognitum Seed | | **Witness chain** | SHA-256 tamper-evident audit trail for every measurement (1,747 entries validated) | Cognitum Seed |
| **Camera-free pose training** | 17 COCO keypoints from 10 sensor signals — PIR, RSSI triangulation, subcarrier asymmetry, vibration, BME280 | 2x ESP32 + Seed | | **Camera-free pose training** | 17 COCO keypoints from 10 sensor signals — PIR, RSSI triangulation, subcarrier asymmetry, vibration, BME280 | 2x ESP32 + Seed |
| **Pre-trained model** | 82.8 KB (8 KB at 4-bit quantization), 100% presence accuracy, 0 skeleton violations | Download from release | | **Pre-trained model** | 82.8 KB (8 KB at 4-bit quantization), 82.3% held-out temporal-triplet accuracy (v1's "100% presence" was single-class — retracted, [#882](https://github.com/ruvnet/RuView/issues/882)) | Download from release |
| **Sub-ms inference** | 0.012 ms latency, 171,472 embeddings/sec on M4 Pro | Any machine with Node.js | | **Sub-ms inference** | 0.012 ms latency, 171,472 embeddings/sec on M4 Pro | Any machine with Node.js |
| **SONA adaptation** | Adapts to new rooms in <1ms without retraining | ruvllm runtime | | **SONA adaptation** | Adapts to new rooms in <1ms without retraining | ruvllm runtime |
| **LoRA room adapters** | Per-node fine-tuning with 2,048 parameters per adapter | Automatic | | **LoRA room adapters** | Per-node fine-tuning with 2,048 parameters per adapter | Automatic |
@ -262,7 +262,7 @@ node scripts/benchmark-ruvllm.js --model models/csi-ruvllm
| What we measured | Result | Why it matters | | What we measured | Result | Why it matters |
|-----------------|--------|---------------| |-----------------|--------|---------------|
| **Presence detection** | **100% accuracy** | Never misses a person, never false alarms | | **CSI embedding quality** | **82.3% held-out temporal-triplet** | Honest label-free metric (v1's "100% presence" was single-class — retracted, [#882](https://github.com/ruvnet/RuView/issues/882)) |
| **Person counting** | **24/24 correct** (MinCut) | Fixed the #1 user-reported issue | | **Person counting** | **24/24 correct** (MinCut) | Fixed the #1 user-reported issue |
| **Inference speed** | **0.012 ms** per embedding | 83,000x faster than real-time | | **Inference speed** | **0.012 ms** per embedding | 83,000x faster than real-time |
| **Throughput** | **171,472 embeddings/sec** | One Mac Mini handles 1,700+ ESP32 nodes | | **Throughput** | **171,472 embeddings/sec** | One Mac Mini handles 1,700+ ESP32 nodes |

6
docs/user-guide.md
View File

@ -1119,7 +1119,7 @@ What it ships (and what it does not):
| Capability | Status | | Capability | Status |
|------------|--------| |------------|--------|
| Presence detection (occupied / empty) | ✅ Trained head — 100% accuracy on validation | | Presence detection (occupied / empty) | ✅ Trained head — v2 encoder reports 82.3% held-out temporal-triplet acc (v1's "100% on validation" was a single-class recording — retracted, [#882](https://github.com/ruvnet/RuView/issues/882)) |
| 128-dim CSI embeddings (re-ID, similarity, downstream training) | ✅ Trained encoder | | 128-dim CSI embeddings (re-ID, similarity, downstream training) | ✅ Trained encoder |
| Single-person breathing / heart-rate | ⚠️ Server still uses heuristic DSP — model does not replace this yet | | Single-person breathing / heart-rate | ⚠️ Server still uses heuristic DSP — model does not replace this yet |
| 17-keypoint full-body pose | 🔬 No keypoint weights shipped yet — pose pipeline runs but without a learned head | | 17-keypoint full-body pose | 🔬 No keypoint weights shipped yet — pose pipeline runs but without a learned head |
@ -1824,7 +1824,7 @@ huggingface-cli download ruvnet/wifi-densepose-pretrained --local-dir models/pre
# model.safetensors — 48 KB contrastive encoder # model.safetensors — 48 KB contrastive encoder
# model-q4.bin — 8 KB quantized (recommended) # model-q4.bin — 8 KB quantized (recommended)
# model-q2.bin — 4 KB ultra-compact (ESP32 edge) # model-q2.bin — 4 KB ultra-compact (ESP32 edge)
# presence-head.json — presence detection head (100% accuracy) # presence-head.json — presence detection head (v2 encoder: 82.3% held-out triplet acc)
# node-1.json — LoRA adapter for room 1 # node-1.json — LoRA adapter for room 1
# node-2.json — LoRA adapter for room 2 # node-2.json — LoRA adapter for room 2
``` ```
@ -1833,7 +1833,7 @@ huggingface-cli download ruvnet/wifi-densepose-pretrained --local-dir models/pre
The pre-trained encoder converts 8-dim CSI feature vectors into 128-dim embeddings. These embeddings power all 17 sensing applications: The pre-trained encoder converts 8-dim CSI feature vectors into 128-dim embeddings. These embeddings power all 17 sensing applications:
- **Presence detection** — 100% accuracy, never misses, never false alarms - **Presence detection** — v2 encoder: 82.3% held-out temporal-triplet accuracy (v1's "100%" was a single-class recording — retracted, [#882](https://github.com/ruvnet/RuView/issues/882))
- **Environment fingerprinting** — kNN search finds "states like this one" - **Environment fingerprinting** — kNN search finds "states like this one"
- **Anomaly detection** — embeddings that don't match known clusters = anomaly - **Anomaly detection** — embeddings that don't match known clusters = anomaly
- **Activity classification** — different activities cluster in embedding space - **Activity classification** — different activities cluster in embedding space