research(R20.2): threshold-based hand-off — works at 0.5 m, harmonic gap at 1 m surfaces Pan-Tompkins requirement (#746)
Implements R20.1's catalogued refinement: when NV conf > 60% AND
amplitude > 3 pT, trust NV entirely.
Mixed result (5 distances):
- 0.5 m: NV=72.00 ✓, smart=72.0 (+0.0 error, NV trusted) ✓
- 1.0 m: NV=144 (harmonic!), smart trusts wrong NV (+72 BPM error)
- 1.5 m+: falls back to weighted (NV conf below threshold)
Production lesson: the threshold-based policy is correct in spirit
but incorrect with simple FFT rate estimator (picks harmonics).
Production needs:
1. Harmonic rejection (Pan-Tompkins QRS or autocorrelation)
2. Cross-check vs breathing band
3. Per-frame plausibility window
R20.1's 'production needs Pan-Tompkins' note is confirmed BINDING,
not nice-to-have, before threshold hand-off can ship.
ADR-114 implementation budget refined: +30-50 LOC for Pan-Tompkins.
Five-step quantum arc:
- R20 vision (tick 37)
- Doc 17 bridge (tick 38)
- ADR-114 spec (tick 39)
- R20.1 working demo (tick 40)
- R20.2 threshold refinement (this tick)
Production ADR-114 cog now has all known refinements catalogued
BEFORE any Rust code is written.
Honest mixed result — catalogue-then-revisit pattern works:
R20.1 flagged production gap; R20.2 attempted fix; fix surfaced
deeper gap (harmonic rejection). Three layers of refinement.
fecb1da252