Automated release from CI pipeline
Changes:
research(R6.2.3): chest-centric placement — +26.9 pp coverage gain for vital-signs cogs (#726)
Direct follow-up from R6.1 (chest contributes 27.6% of CSI energy,
5x per-limb value, limbs are confound not signal).
R6.2.3 re-runs R6.2's placement search with chest-only target zones
(40x40 cm patches at expected chest positions) vs body-footprint zones
(R6.2's default full-area definition).
Headline result:
| Configuration | Coverage | Placement |
|---|---|---|
| Body-centric (R6.2 default) | 49.3% | (4.25,0)-(0,3.25), 5.35 m |
| CHEST-CENTRIC (R6.2.3 new) | 82.4% | (2.0,0)-(4.5,5), 5.59 m |
Cross-eval:
- Body-optimal on chest zones: 55.5%
- Chest-targeting GAIN on chest: +26.9 pp
- Chest-optimal on body zones: 40.3% (-9.0 pp loss)
The two strategies are genuinely different. Same engine, different
zones.
Per-cog deployment recommendation surfaced:
- --target-mode=body (default): cog-person-count, cog-pose, cog-presence
- --target-mode=chest (new): cog-vital-signs, cog-breathing, cog-HR
- --target-mode=extremity (future): gesture detection
~20 LOC change to R6.2 CLI.
R14 vertical-specific:
- V1 stress-responsive lighting: chest mode
- V2 adaptive HVAC (presence+breathing): mixed
- V3 attention-respecting conversation: chest mode
R6.2.3 surfaces a per-cog config that empathic-appliance products
need at install time.
Why placements differ: when target ~ envelope width, envelope can cover
it entirely; when target >> envelope, placement must compromise. 40 cm
Fresnel envelope @ 5 m link comfortably covers 40 cm chest patches but
must spread to cover 3 m^2 bed.
Composes:
- R6.1 motivated this tick
- R6.2 / R6.2.1 / R6.2.2 -- orthogonal extensions
- R14 V1/V3 should use chest mode
- R12 PABS improves body-position-detection scenarios
Honest scope:
- Chest positions approximated
- 2D still (3D chest-centric = R6.2.3.1 follow-up)
- Single subject (multi-subject = union of chest envelopes)
- Per-cog zone schema is deployment-time
Coordination: ticks/tick-23.md, no PROGRESS.md edit.
Docker Image:
ghcr.io/ruvnet/RuView:8b850d8b2abf1dea52d87fa63f752333889ba357