docs: retract stale '100% presence accuracy' headlines (single-class; superseded by honest 82.3% held-out triplet metric, RuView #882)

README.md

@@ -28,7 +28,7 @@ WiFi signals bounce off people. When someone breathes, their chest moves the air
 
 | What it senses | How well | Without |
 |----------------|----------|---------|
-| **Is someone there?** | 100% accuracy | No camera needed |
+| **Is someone there?** | presence detection (v1 "100%" retracted — single-class) | No camera needed |
 | **Are they moving?** | Detects typing vs walking vs standing | No wearable needed |
 | **Breathing rate** | 6-30 BPM, contactless | No chest strap |
 | **Heart rate** | 40-120 BPM, through clothes | No smartwatch |
@@ -91,7 +91,7 @@ Validated on real hardware (Apple M4 Pro + 2x ESP32-S3):
 
 | Metric | Result | Context |
 |--------|--------|---------|
-| **Presence accuracy** | **100%** | Never misses, never false alarms |
+| **CSI embedding quality** | **82.3% held-out** | Honest temporal-triplet metric; v1 single-class "100% presence" retracted (#882) |
 | **Inference speed** | **0.008 ms** | 125,000x faster than real-time |
 | **Throughput** | **164,183 emb/sec** | One laptop handles 1,600+ sensors |
 | **Contrastive learning** | **51.6% improvement** | Trained on 8 hours of overnight data |
@@ -107,7 +107,7 @@ Validated on real hardware (Apple M4 Pro + 2x ESP32-S3):
 | `model-q4.bin` | 8 KB | **Recommended** — 4-bit quantized, 8x compression |
 | `model-q2.bin` | 4 KB | Ultra-compact for ESP32 edge inference |
 | `model-q8.bin` | 16 KB | High quality 8-bit |
-| `presence-head.json` | 2.6 KB | Presence detection head (100% accuracy) |
+| `presence-head.json` | 2.6 KB | Presence detection head (v1 "100%" retracted — single-class; #882) |
 | `node-1.json` | 21 KB | LoRA adapter for room/node 1 |
 | `node-2.json` | 21 KB | LoRA adapter for room/node 2 |
 | `config.json` | 586 B | Model configuration |
@@ -145,7 +145,7 @@ WiFi signals → ESP32-S3 ($9) → 8-dim features @ 1 Hz → Encoder → 128-dim
                                          ┌──────────────────────────┼──────────────────┐
                                          ↓                          ↓                  ↓
                                     Presence head            Activity head         Vitals head
-                                    (100% accuracy)          (still/walk/talk)     (BR, HR)
+                                    (v1 "100%" retracted)          (still/walk/talk)     (BR, HR)
 ```
 
 The encoder converts 8 WiFi Channel State Information (CSI) features into a 128-dimensional embedding: