From dac40e5df226bebe037fc1b3fdce57c5a6425b68 Mon Sep 17 00:00:00 2001 From: ruv Date: Sun, 31 May 2026 03:01:50 -0400 Subject: [PATCH] docs(adr-150): calibration thesis is task-general (action recognition) Verified on a 2nd MM-Fi task: 27-class action recognition (which MM-Fi never benchmarked for WiFi; only published baseline WiDistill 34%). In-domain 88% (leaky); cross-subject zero-shot collapses to ~10%; few-shot calibration rescues 10->76% (1000 samples). Same mechanism as pose -> few-shot in-room calibration is the universal WiFi-sensing generalization answer, not a pose quirk. Co-Authored-By: claude-flow --- docs/adr/ADR-150-rf-foundation-encoder.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/docs/adr/ADR-150-rf-foundation-encoder.md b/docs/adr/ADR-150-rf-foundation-encoder.md index b3cccb3d..bb80ab25 100644 --- a/docs/adr/ADR-150-rf-foundation-encoder.md +++ b/docs/adr/ADR-150-rf-foundation-encoder.md @@ -174,6 +174,13 @@ need fewer calibration frames" — a better-posed, achievable objective. **This pessimism: the frontier is not closed by algorithms or bulk data, but it *is* cheaply closed at deployment time by few-shot calibration.** +> **Task-general (2026-05-31).** The same mechanism was verified on a *second* MM-Fi task — +> 27-class **action recognition** (which the MM-Fi paper never benchmarked for WiFi). Zero-shot +> cross-subject collapses to ~10% (near-chance), and few-shot calibration recovers it: 50 samples → +> 36%, 200 → 59%, 1000 → 76%. Action needs more calibration than pose (classification vs regression), +> but the pattern is identical. **Few-shot in-room calibration is the universal deployment answer for +> WiFi sensing generalization, not a pose-specific result.** (Optimization report §36.) + ### 3.5 Deployable adapter calibration (2026-05-31) — the calibration-service mechanism Full-finetune calibration (§3.4) means a 2.3 MB model copy per room. Compared calibration methods at