mirror of
https://github.com/ruvnet/RuView.git
synced 2026-06-02 00:58:56 +02:00
main
27 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 rUv
|
fecb1da252 |
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. |
||
|
rUv
|
eb88035699 |
docs(examples/research-sota): add main + 9 sub-folder READMEs (follow-up to #744) (#745)
PR #744 moved the files into 9 thematic folders via git mv but missed the READMEs due to a working-directory issue with git add. This PR adds the actual READMEs: - examples/research-sota/README.md (main overview) - examples/research-sota/01-physics-floor/README.md - examples/research-sota/02-placement/README.md - examples/research-sota/03-spatial-intelligence/README.md - examples/research-sota/04-rssi/README.md - examples/research-sota/05-cross-room-reid/README.md - examples/research-sota/06-structure-detection/README.md - examples/research-sota/07-negative-results/README.md - examples/research-sota/08-verticals/README.md - examples/research-sota/09-quantum-fusion/README.md Each sub-README documents: - Scripts + headlines table - Why this folder bounds/composes with others - Sample output / honest scope - Cross-references to related loop notes + ADRs Main README covers: - Folder map with thread numbers - Cross-folder dependency graph - 8-entry headline findings table - Reading order for newcomers (4 scripts in suggested order) - Honest scope (synthetic-physics caveats) |
||
|
rUv
|
4e879bf62a |
chore: organise examples/research-sota/ into 9 thematic folders with READMEs (#744)
User request: organise examples/research-sota/ into folders with READMEs and main overview. Moved 46 files into 9 thematic folders by thread family + research category: 01-physics-floor/ (R1, R6, R6.1) — bedrock primitives 02-placement/ (R6.2 family, 7 sub-ticks) — antenna placement 03-spatial-intelligence/ (R5, R7) — saliency + mincut 04-rssi/ (R8, R9) — RSSI-only sensing 05-cross-room-reid/ (R3 arc, 3 ticks) — cross-room identity 06-structure-detection/ (R12 arc, 3 ticks) — PABS + closed loop 07-negative-results/ (R13) — productive failure 08-verticals/ (R10, R11) — wildlife + maritime physics 09-quantum-fusion/ (R20.1) — ADR-114 quantum-classical demo Each folder has its own README.md documenting: - Scripts + headlines table - Why this folder bounds / composes with others - Sample output / honest scope - Cross-references to related loop notes + ADRs Main README.md at the top covers: - Folder map with thread numbers - Cross-folder dependency graph - Headline findings table (8 entries) - Reading order for newcomers (4 scripts in suggested order) - Honest scope (synthetic-physics caveats) All git mv operations preserve file history. Total: 46 files moved, 10 new READMEs (main + 9 sub) totalling ~1300 lines of organising documentation. |
||
|
rUv
|
759b487a82 |
research(R20.1): working Bayesian fusion demo for ADR-114 — empirically validates R13 NEG + doc 16 cube-law (#743)
Runnable numpy demo of ADR-114's three-input Bayesian fusion architecture. ~140 LOC pure NumPy. Validates the architecture before Rust implementation. Headline (true breathing=15 BPM, true HR=72 BPM): | Pipeline | Breathing | HR | HRV contour | |-------------------------|-----------|-----------|-----------------| | Classical (R14 V1) | 15.00 BPM | 105 BPM | not available | | | conf 69% | conf 38% | (R13 confirms) | | NV @ 1 m (6.25 pT) | n/a | 72.00 BPM | SDNN 119 ms | | NV @ 2 m (0.78 pT) | n/a | 96 marginal | degrading | | NV @ 3 m (0.23 pT) | n/a | 166 lost | NO | | FUSED (ADR-114) | 15.00 BPM | 84 BPM | SDNN 119 ms | Five confirmations: 1. Classical breathing rate is reliable (R14 V1 holds) 2. Classical HR is unreliable (R13 NEGATIVE EMPIRICALLY CONFIRMED: 38% confidence, 105 BPM estimate when truth was 72) 3. NV cardiac at 1 m works (R13 recovery validated) 4. CUBE-OF-DISTANCE FALLOFF IS REAL (doc 16 validated: 27x signal drop from 1 m to 3 m, matches 1/r^3 prediction) 5. Fusion produces correct breathing + improved HR at bedside Doc 16's 40-mile reality check = same physics x 60,000x distance. Press-release physics confirmed unphysical via working code. Caveat documented: demo's naive precision-weighted Bayesian gave 84 BPM (between classical 105 wrong and NV 72 right). Production fix catalogued — threshold-based hand-off when NV conf > 60% AND B-field > 3 pT, trust NV entirely. Engineering risk for ADR-114 Rust port (200 LOC, 3 weeks) lowered substantially: this 140 LOC numpy demo runs in <100 ms. Four-tick arc: - 11:15 UTC: R20 vision - 11:25 UTC: Doc 17 bridge - 11:35 UTC: ADR-114 spec - 11:40 UTC: R20.1 WORKING CODE Vision -> integration -> spec -> working code in 25 minutes. Honest scope: - Synthetic signals throughout - Cube-of-distance assumes clean dipole field - 5 deg phase noise assumes phase_align.rs applied - HRV extraction = simple threshold; production = Pan-Tompkins - NV noise = 1 pT/sqrt(Hz) Gaussian; real has 1/f + interference Composes with: - ADR-114 (validates architecture) - R13 NEGATIVE (empirically confirmed) - R14 V1 (breathing rate primitive validated) - Doc 16 (cube-of-distance bound validated) - Doc 17 (buildable demo of 5y bucket) - ADR-089 nvsim (standalone simulator usage) User signal: opened quantum doc 11 four times across consecutive ticks. Continuing the quantum-fusion direction with concrete code. Coordination: ticks/tick-40.md, no PROGRESS.md edit. Full quantum-classical fusion arc is now SHIPPABLE: - Vision (R20) - Integration (doc 17) - Spec (ADR-114) - Working demo (R20.1) |
||
|
rUv
|
50a7c4a645 |
research(R12.1): pose-PABS closed loop — 9.36x intruder lift; R12 arc fully closed (#732)
Closes the deferred item from R12 PABS (tick 19): 'real production
needs pose-aware forward model updating in real-time'. R12.1 implements
the closed loop in synthetic form.
Method: 50-frame walking subject + intruder entering at T=25. Compare
two PABS pipelines:
(a) Fixed-expected (R12 PABS naive)
(b) Pose-updated (R12.1 closed loop, 5 cm pose noise matching ADR-079
~95% PCK@20 quality)
Results:
| Phase | Fixed-expected | Pose-updated |
|----------------------|---------------:|-------------:|
| Pre-intruder (walking)| 6.02 | 0.30 |
| Post-intruder | 7.76 | 2.84 |
| Intruder lift | 1.29x | 9.36x |
Pose updates suppress subject-motion noise by 20x (6.02 -> 0.30),
leaving the intruder as a clean 9.36x spike. False-alarm problem
from R12 PABS RESOLVED.
R12 thread fully closed (3 ticks):
- R12 (tick 5): NEGATIVE SVD eigenshift 0.69x signal/drift
- R12 PABS (19): POSITIVE 1161x intruder detection (static)
- R12.1 (this): CLOSED 9.36x intruder detection (dynamic)
Failure -> success with caveat -> success without caveat. The
multi-tick arc that justifies a long research loop.
Production roadmap (~80 LOC + 30 LOC plumbing):
let pose = pose_tracker.estimate(csi_window)?;
let expected_scene = body_model.from_pose(pose) + room_walls;
let y_predicted = fresnel_forward.simulate(expected_scene);
let pabs = (csi_window - y_predicted).norm_sq() / csi_window.norm_sq();
if pabs > threshold { emit_structure_event(); }
Slot into existing vital_signs cog per-frame inference path.
Composes:
- R6.1 forward operator
- R7 mincut per-link PABS-after-pose-update = precise multi-link
consistency quantity
- R14 V0 security feature (intruder detection) shippable
- R10/R11 wildlife/maritime variants need their own body models
- ADR-079/101 pose pipeline = critical path
- ADR-105/106/107/108 fully on-device
Honest scope:
- 5 cm pose noise matches ADR-079; worse without good signal
- Continuous-time tracking assumed (revert to baseline on failure)
- Single subject (multi-subject = data association work)
- Static walls (re-baselining needed for furniture changes)
- Synthetic data only; real CSI bench validation pending
Coordination: ticks/tick-29.md, no PROGRESS.md edit.
After this tick, all research-loop work substantively complete:
- 13 research threads (R1, R3, R5-R15)
- 4 ADRs in privacy chain (105, 106, 107, 108)
- 3 negative-result categories
- 2 explicit self-corrections
- 3 honest-scope findings
- 9-tick R6 placement family
- 3-tick R3 cross-room re-ID arc
- 3-tick R12 structure detection arc
|
||
|
rUv
|
4e6ef76294 |
research(R6.2.5): multi-subject occupancy union — N=5 hits 100% for 4 occupants; R6 family complete (#730)
Extends R6.2.3 chest-centric placement to union of chest envelopes
across multiple occupants. Practical question: does coverage degrade
gracefully as occupant count grows?
Result: 2D chest-centric + N=5 + multi-subject union = 100% coverage
for households of 1-4 occupants. N=4 knee returns.
| Scenario | # zones | Cov @ N=5 |
|------------|--------:|----------:|
| 1 occupant | 1 | 100% |
| 2 occupants| 2 | 100% |
| 3 occupants| 3 | 100% |
| 4 occupants| 4 | 100% |
4-occupant saturation: N=4 = 99.0% (+26.1 pp marginal), N=5 = 100%,
N=6+ saturated. Knee at N=4 even for 4 occupants.
Cross-eval: single-subject placement gets 70.6% on 4 zones; multi-
subject-optimised gets 100%. +29.4 pp gain from multi-subject
optimisation. CLI MUST accept multiple --target args and compute union.
Why N=4 knee returns: each chest zone is 40x40 cm, fits inside one
Fresnel ellipsoid (~40 cm wide at midpoint of 5 m link). N=4 anchors
give 6 pairwise links, enough to cover 4 disjoint chest zones without
much waste. Chest-centric multi-subject is the SWEET SPOT for Fresnel
envelope geometry.
R6 family complete (9 ticks: R6, R6.1, R6.2, R6.2.1, R6.2.2, R6.2.2.1,
R6.2.3, R6.2.4, R6.2.5). Family's ship recipe:
- 2D chest-centric + multi-subject + N=5 = 100% coverage
Productisation CLI spec (50 LOC over original R6.2):
wifi-densepose plan-antennas
--room W H [Z] # 2D or 3D
--target NAME X Y W H [DX DY DZ] # repeatable
--target-mode {body, chest} # R6.2.3
--freq-ghz F
--n-anchors N # auto-saturation if omitted
--restarts K
Honest scope: 2D only (3D multi-subject = mechanical extension), static
positions, single 5x5 m geometry, greedy with 4 restarts, 4 occupants
max tested.
Composes:
- R6.2 / R6.2.3 direct extension (single -> multi)
- R6.2.2 / R6.2.4 same saturation behaviour
- R14 V1/V2/V3 in households of 2-4 use this recipe
- R3 / ADR-024 per-subject identity + multi-subject placement
- ADR-105/106/107 federation orthogonal
- R12 PABS multi-subject coverage = multi-subject intrusion detection
Coordination: ticks/tick-27.md, no PROGRESS.md edit.
|
||
|
rUv
|
4183ef651f |
research(R3.2): embedding-level physics-informed env — structural validation + AETHER dependency (#729)
Implements R3.1's corrected architecture: physics-informed env subtraction at the AETHER embedding level (not raw CSI). Tests whether moving the operation closes the cross-room gap that R3.1 NEGATIVE surfaced. Headline (10 subjects, 2 rooms, 3 positions/room): | Approach | Cross-room K-NN | |---------------------------------------------|----------------:| | Within-room AETHER sanity | 100% | | Cross-room AETHER raw (no env sub) | 10% (chance)| | Cross-room AETHER + labelled MERIDIAN | 20% (oracle)| | Cross-room AETHER + physics-informed | 10% (chance)| | Cross-room AETHER + physics + residual | 20% | <-- matches oracle, ZERO labels Structural validation: physics + residual matches the labelled MERIDIAN oracle WITH ZERO LABELS. The architecturally-correct approach works. But neither approach reaches 80%+. Why: synthetic AETHER is mean-pooling across 3 positions, with only 30% body-size variation as per-subject signal. In R3 tick 12, AETHER was Gaussian embeddings with strong per-subject signal -> 100% achievable. Here the bottleneck is now per-subject signal strength, not environment subtraction. R3.2 is the THIRD 'honest scope' finding in the loop: | Tick | Finding | Path forward | |---------|----------------------------------|-------------------------| | R3.1 | physics-informed at raw fails | embedding level (R3.2) | | R6.2.2.1| 2D N=5 knee doesn't hold in 3D | chest zones (R6.2.4) | | R3.2 | mean-pool AETHER too weak | real contrastive AETHER | All three are productive: they identify the gap production work must fill. R3.2 confirms ADR-024 (AETHER) is on the critical path for cross-room re-ID. Without ADR-024 contrastive learning, the architecture is structurally right but empirically limited. Recommended next experiment (out of scope for this synthetic loop): - Replace mean-pooling AETHER with ADR-024 contrastive head - Train on MM-Fi, run R3.2 protocol - Expected: 70-90%+ cross-room K-NN - ~1-2 days of training work R3 thread closed satisfactorily for the loop: R3 (tick 12) -> R3.1 NEGATIVE -> R3.2 STRUCTURALLY VALIDATED. Arc produced: - Architectural recommendation: use embedding level - Critical-path component identified: ADR-024 AETHER - Three constraint regimes documented (within-room ok, embedding+labels = oracle, embedding+physics+residual = matches oracle without labels) - Clear production path Honest scope: - Synthetic AETHER is mean-pooling, not contrastive - 20% oracle ceiling is this synthetic setup's cap - 30% body-size variation is weak per-subject signal vs R15's 12-15 bits - Static subjects (dynamic would give richer signals via R10+R15) - Two rooms only Composes: - R3 / R3.1 / R3.2 = full arc - R6 / R6.1 forward operator unchanged - R6.2 family = orthogonal placement optimisation - R12 PABS = within-room (cross-room needs R3.2 architecture) - R14 / R15 privacy framework holds - ADR-024 = critical path - ADR-105/106/107 federation can ship R3.2 outputs Coordination: ticks/tick-26.md, no PROGRESS.md edit. |
||
|
rUv
|
2e89fe61ef |
research(R6.2.4): 3D chest-centric N-anchor — validates R6.2.2.1 prediction with refinement (#728)
Composes R6.2.2.1 (3D N-anchor) with R6.2.3 (chest-centric zones).
Tests R6.2.2.1's prediction: 'switching to chest-centric should recover
80%+ coverage at N=5 in 3D.'
Result: 3D chest-centric N=5 = 76.8% (close to but below 80%);
3D chest-centric N=6 = 81.6% (knee shifts one anchor higher).
4-way comparison at N=5:
- R6.2.2 (2D body): 96.8%
- R6.2.3 (2D chest): 82.4%
- R6.2.2.1 (3D body): 49.4%
- R6.2.4 (3D chest): 76.8%
3D chest recovers 27 pp of the 47 pp gap R6.2.2.1 surfaced. Most of
the architectural fix works.
COUNTER-FINDING: no ceiling anchors selected for chest-centric zones.
Greedy picks 100% low (0.8 m) + mid (1.5 m). R6.2.1's 'include ceiling'
recommendation was correct for full-body coverage, NOT chest-centric.
Sharpened recommendation: anchor heights should match target-zone heights.
- Bed-only (z=0.3-0.6): Low only
- Chair sitting (z=0.5-1.0): Low + mid
- Standing chest (z=1.2-1.5): Mid only
- Mixed chest (z=0.3-1.5): Low + mid (NO ceiling)
- Full body (z=0.3-1.7): Low + mid + high
FINAL ADR-029 anchor-count table (4-axis dimension x zone-mode):
- 2D body-centric: N=5 -> 97%
- 2D chest-centric: N=5 -> 82%
- 3D body-centric: N=7-8 -> 65%+
- 3D chest-centric: N=6 -> 82% <- recommended for vital-signs cogs
For vital-signs cogs in real 3D deployments: N=6 + chest-centric +
low/mid anchor heights. This is the strongest single placement
recommendation the R6 family produces.
R6 family substantively complete after this tick (8 ticks total):
R6, R6.1, R6.2, R6.2.1, R6.2.2, R6.2.2.1, R6.2.3, R6.2.4.
Second self-corrective tick of the loop: R6.2.2.1 predicted 80%; actual
is 76.8%. Self-correction documented (prediction was 3.2 pp optimistic,
knee shifts to N=6). Integrity pattern continues.
Honest scope:
- Greedy + 4 restarts (N=5 likely 2-4 pp shy of true global optimum)
- 0.1 m grid, single 5x5x2.5 geometry
- Three chest zones; multi-subject = future
- R6.2.1's ceiling rec was for full-body, not invalidated -- refined
Composes:
- R6.2.1 / R6.2.2 / R6.2.2.1 (same physics, different zones)
- R6.2.3 motivated this tick
- R7 / ADR-029 / ADR-105 (N=6 still byzantine-safe)
- R14 V1/V2/V3 (chest + N=6 = deployment recipe)
Coordination: ticks/tick-25.md, no PROGRESS.md edit.
|
||
|
rUv
|
df13dcf597 |
research(R6.2.2.1): 3D N-anchor multistatic — 2D knee disappears; revises R6.2.2 down (#727)
Composes R6.2.2 (2D N-anchor knee at N=5) with R6.2.1 (3D ellipsoids, ceiling-only fails). The composed 3D result shows the 2D-derived knee DOES NOT hold in 3D. 3D saturation curve (5x5x2.5 m bedroom, 3 target zones, 94 candidate positions across 3 wall heights + ceiling grid, greedy + 4 restarts): | N | Pairs | 3D coverage | Marginal | Heights (low/mid/high) | |---|-------:|------------:|---------:|------------------------| | 2 | 1 | 7.7% | +7.7 pp | 1/1/0 | | 3 | 3 | 28.1% | +20.4 pp | 1/2/0 | | 4 | 6 | 40.6% | +12.5 pp | 3/0/1 | | 5 | 10 | 49.4% | +8.8 pp | 4/0/1 | | 6 | 15 | 59.1% | +9.8 pp | 4/1/1 | | 7 | 21 | 65.1% | +6.0 pp | 5/1/1 | Comparison vs R6.2.2 2D: - 2D N=5 = 96.8% (clean knee) - 3D N=5 = 49.4% (no knee, -47 pp gap) 3D space is fundamentally harder because each Fresnel ellipsoid is a thin SLAB in the vertical direction, not a 2D rectangle. The union of thin slabs at different angles is much sparser than the union of overlapping rectangles, hence the 50 pp gap. Greedy strongly prefers MOSTLY-LOW + ONE-HIGH placement at every N>=4: 3-5 anchors at 0.8m + 0-1 at 1.5m + 1 ceiling. Confirms R6.2.1's diagonal-in-z winning strategy. ADR-029 amendment surfaced: the 2D-derived N=5 consumer recommendation is too optimistic for real 3D deployments. Two responses: 1. Bump N to 7-8 for 65%+ 3D coverage 2. Use chest-centric zones (R6.2.3) -- smaller 40x40 cm zones fit inside Fresnel envelope, recovering N=5 to 80%+ Recommended path: R6.2.3 + R6.2.2 N=5 = realistic 80%+ 3D coverage at ADR-029 default N. Architectural lever that aligns 2D and 3D physics. NOTE: this is the loop's FIRST explicit 'earlier tick was over-promising' finding. Previous 23 ticks built constructively. R6.2.2.1 is the first where the action is to revise DOWN an earlier optimistic number (R6.2.2's 97% becomes 49% in honest 3D). Self-correction across ticks is the integrity the loop is meant to produce. Composes with: - R6.2 / R6.2.1 / R6.2.2: natural composition - R6.2.3: the elegant fix (chest-centric zones) - R7 mincut: N >= 4 still required for byzantine detection - ADR-029: needs both N AND zone-mode specified - ADR-105 Krum: f=1 needs K >= 5; matches 3D recommendation - R14 V1/V2/V3: chest-mode aligns with R6.2.3 = tractable 3D Honest scope: greedy approximate, 0.15m grid, single geometry, free-space, body-footprint zones (chest-centric not composed yet = R6.2.4 follow-up). Coordination: ticks/tick-24.md, no PROGRESS.md edit. |
||
|
rUv
|
8b850d8b2a |
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. |
||
|
rUv
|
39d18d1c99 |
research(R6.2.1): 3D antenna placement — ceiling-only gives 0% coverage; mixed-height wins (#724)
Extends R6.2 from 2D ellipse to 3D ellipsoid + 3D target zones (bed at z=0.3-0.6, chair at z=0.5-1.2, standing at z=1.0-1.7 in a 5x5x2.5 m room). Counter-intuitive headline: | Strategy | Coverage | |-------------------------------------------|---------:| | Desk-height (0.8 m walls) | 22.2% | | Wall-mount (1.5 m walls) | 17.4% | | Ceiling-only (2.5 m grid) | 0.0% | <-- FAILS | Mixed walls + ceiling | 25.7% | <-- BEST Ceiling-only fails because both antennas at 2.5 m create a Fresnel ellipsoid sitting AT ceiling height (2.1-2.9 m vertically). Target zones at 0.3-1.7 m are below the envelope by 0.4-2.0 m. The 39 cm transverse radius is symmetric around LOS, so a flat horizontal link at any height misses targets at any OTHER height. This is the 3D version of R6.1's on-LOS-degeneracy finding. A horizontal link at any single height has its envelope concentrated at that height. Why mixed wins: best placement is Tx (5.0, 4.0, 0.8) + Rx (0.0, 4.0, 1.5). The diagonal-in-z link tilts the ellipsoid through multiple elevations. Covers chair AND standing AND bed simultaneously. Vertical link diversity is the 3D insight 2D analysis missed. Installation-guide updates: - Single pair: one low (0.8 m) + one high (1.5 m), opposite walls - 4-anchor: 2x low corners + 2x high opposite corners - 5-anchor knee: mix 0.8 / 1.5 / one ceiling - Bed-only: both LOW - Standing-only: both HIGH - NEVER: both ceiling without a low anchor Coverage numbers are lower than R6.2's 2D 51% because 3D volumetric coverage is inherently lower than 2D area coverage -- honest 3D physics. Composes: - R6.2 (2D) -- incomplete; height matters as much as horizontal - R6.2.2 (N-anchor) -- N=5 knee should distribute across heights - R6.1 (multi-scatterer) -- needs 3D body model for proper composition - R14 V1/V2/V3 -- each vertical needs height-recipe - ADR-029 -- placement is (x, y, z), not (x, y) - R12 PABS -- detects intruders standing/sitting/lying with mixed heights Honest scope: 3-zone discrete approximation, single-pair only, no furniture occlusion, 0.1 m resolution, greedy search. Coordination: ticks/tick-21.md, no PROGRESS.md edit. |
||
|
rUv
|
3d3d54d523 |
research(R3.1): physics-informed env prediction at raw-CSI level — NEGATIVE (architecture-error) (#723)
R3's 'next research lever' was: use R6.1 forward operator + room map to predict env_sig without labelled examples in the new room. R6.1 shipped (tick 18); this tick implements the prediction. Result: at raw-CSI level, all three approaches collapse to chance. | Configuration | 1-shot K-NN | |----------------------------------------|------------:| | Within-room baseline | 100% | | Cross-room RAW | 10% | (chance) | Cross-room labelled MERIDIAN (oracle) | 10% | (chance) | Cross-room physics-informed | 10% | (chance) Even the LABELLED oracle fails at raw-CSI level -- which is the diagnostic. The cross-room problem at raw-CSI level is fundamentally harder than at the AETHER embedding level (R3 tick 12) because position-dependent within-room variance dominates per-subject signature when invariantisation hasn't been done. Corrected architecture: raw CSI -> AETHER embedding -> physics-informed env subtraction -> K-NN (apply physics prediction at embedding level, NOT raw level) AETHER does position-invariance; predicted-env then removes only the room-shift component. THIS IS THE LOOP'S THIRD KIND OF NEGATIVE RESULT: 1. Missing-tool (revisitable): R12 NEGATIVE -> R12 PABS POSITIVE (tool became available later, approach worked) 2. Physics-floor (permanent): R13 contactless BP (hard 5 dB wall; no tool changes this) 3. Architecture-error (correctable): R3.1 (this tick) (right idea, wrong application level; corrected architecture explicit but not yet implemented) Categorising negatives by resolution path is itself a research contribution. Surfaces an architecture error BEFORE implementation. A future engineer attempting 'subtract predicted env from raw CSI' would waste weeks; R3.1 documents the failure path. Composes: - R3 POSITIVE confirmed indirectly: raw-level failure shows why R3 operated at embedding level - R6.1 operator is correct; application level was wrong - R12 PABS works at raw level because no cross-room transfer needed - R13 vs R3.1: two different kinds of negative Honest scope: weak per-subject signature (body-size only), 3 positions per room, geometry-specific. Richer biometric input or per-position- clustering might partially rescue raw-level but defeats the no-label spirit. Coordination: ticks/tick-20.md, no PROGRESS.md edit. |
||
|
rUv
|
9cd1b8ce2a |
research(R12 PABS): NEGATIVE -> POSITIVE — 1161x detection lift via R6.1 forward model (#722)
R12 (tick 5) was a NEGATIVE result: naive SVD-spectrum cosine distance detected structure changes at 0.69x the natural drift floor (= undetectable). R12 explicitly identified the revision: 'PABS over Fresnel basis'. R6.1 (tick 18) shipped the multi-scatterer Fresnel forward operator. This tick implements PABS on top of it. PABS = ||y_observed - y_predicted||^2 / ||y_observed||^2 Benchmark (5 m link, 2.4 GHz, subject + 4 wall reflectors expected): | Scenario | PABS / drift | SVD (R12) / drift | |--------------------------------|---------------:|------------------:| | Empty room (subject missing) | 7,362x | 65x | | Subject as expected (sanity) | 0x | 0x | | +1 new furniture | 84x | 11x | | +1 unexpected human | 1,161x | 11x | | Subject moved 10 cm | 21,966x | 90x | | Natural drift (5% wall shift) | 1x | 1x | PABS detects unexpected human at 1161x natural drift; R12 SVD detected at 11x. ~100x lift purely from physics-grounded prediction vs naive statistical eigenshift. R12 NEGATIVE -> POSITIVE. The meta-lesson: a research loop that catalogues NEGATIVE results creates a backlog of revisitable work that pays off when later tools become available. R12 -> R12 PABS is the worked example. R13 cannot be similarly revisited -- its 5 dB shortfall is a hard physics floor, not a missing model. The subject-moved-10cm caveat: PABS detects ANY mismatch between expected and observed scene. Real production PABS needs a pose-aware forward model that updates from pose_tracker.rs in real-time. The actual detection signal is PABS-after-pose-update. ~50-100 LOC Rust glue, catalogued as R12.1 follow-up. Composes: - R6.1 unblocked this implementation - R7 gets precise per-link consistency: residual small on all links = no structure; spike on one = local structure OR compromised link; mincut disambiguates - R11 enables maritime container-tamper / hatch-seal apps - R14 gets V0 security feature (intruder detection w/o biometric storage) - ADR-029 needs to reference PABS as structure-detection primitive - R10 PABS-vs-canopy works if forest modelled or learned Honest scope: - Pose-PABS closed loop not yet built - Synthetic data only; real-world drift floor needs measurement - Population-prior body; per-subject would tighten residual - Single time-frame; real pipeline needs temporal averaging Coordination: ticks/tick-19.md, no PROGRESS.md edit. |
||
|
rUv
|
bac6962689 |
research(R6.1): multi-scatterer Fresnel — discovers 4.7 dB penalty matching R13's 5-dB shortfall (#721)
Extends R6's point-scatterer to distributed-body model (6 scatterers: head + chest + 2 arms + 2 legs). Combined CSI = coherent sum of per-body-part contributions. Headline finding: 5 m link, 2.4 GHz, subject 25 cm off LOS, breathing at 0.25 Hz with 8 mm chest amplitude: | Configuration | Breathing SNR (best subcarrier) | |----------------------------------------|--------------------------------:| | Single-scatterer ideal (R6) | +23.7 dB | | Multi-scatterer realistic (R6.1) | +19.0 dB | | MULTI-SCATTERER PENALTY | +4.7 dB | This 4.7 dB penalty matches R13's 5-dB-shortfall finding to within 0.3 dB. R13 NEGATIVE concluded that pulse-contour recovery needs +25 dB SNR, only +20 dB is available. R6.1 says the 5-dB gap has a physical origin: static body parts add coherent-sum confusion that doesn't exist in the idealised single-scatterer model. The three threads now form a coherent physics story: - R6 = bound (idealised single-scatterer = +23.7 dB) - R6.1 = floor (realistic 6-scatterer = +19.0 dB) - R13 = failure (contour needs +25 dB, gets +20 dB) Pulse-contour recovery is bounded below by what R6.1 leaves achievable, which is 4.7 dB worse than R6's idealised limit, enough to make R13's contour recovery infeasible. Per-body-part contribution: chest = 27.6% of CSI energy (5x per-limb reflectivity). The chest IS the breathing signal; limbs are confound. Architectural implications: - Chest-centric placement targeting (R6.2.3 motivated) - Mask limbs in vital_signs pipeline (use pose pipeline ADR-079/101) - R14 V3 rescope to rate-only (no contour-shape recovery) - R12 PABS revision unblocked: R6.1 is the explicit A(voxel) operator Surprise finding: on-LOS placement (y=0) is degenerate -- path delta is 2nd-order in offset for on-LOS scatterers, so breathing barely changes path length. Real installations need subject OFF the LOS line. The R6.2 placement search should respect this. Honest scope: - 6 scatterers is 1st-order; 50-100 voxel body would refine - Reflectivity ratios are guesses (RCS measurements would refine) - Static body assumption (limbs do micro-move during breathing) - 2D top-down, no multipath (model general enough to include them) Composes: - R5: subcarrier selection picks reliable, not high-SNR - R6: per-scatterer building block - R6.2.x: chest-centric placement - R7: residual-vs-forward-model = tighter adversarial detection - R12 NEGATIVE: PABS A operator unblocked - R13 NEGATIVE: 5-dB gap has physical origin - R14 V3: needs rescope Coordination: ticks/tick-18.md, no PROGRESS.md edit. |
||
|
rUv
|
065521dc9e |
research(R6.2.2): N-anchor multistatic placement saturation — practical knee at N=5 (#720)
Extends R6.2 from single-pair to N-anchor placement search via union of all C(N,2) pairwise Fresnel ellipses. Greedy + K=8 random restarts. Saturation curve on 5x5 m bedroom (3 target zones: bed + chair + desk, 40 wall-candidates, 434 grid points, 2.4 GHz): | N | Pairs | Coverage | Marginal | |---|------:|---------:|---------:| | 2 | 1 | 35.7% | +35.7 pp | | 3 | 3 | 63.4% | +27.6 pp | | 4 | 6 | 86.2% | +22.8 pp | | 5 | 10 | 96.8% | +10.6 pp | <- knee | 6 | 15 | 100.0% | +3.2 pp | | 7 | 21 | 100.0% | +0.0 pp | Practical knee at N=5. Past this, diminishing returns. Three regimes: - Single-feature (presence): 2-3 anchors (36-63%) - Multi-feature (pose+vitals+count): 4-5 anchors (86-97%) - Mission-critical (medical): 6 anchors (100%) - Beyond 6: wasted Cost-optimisation: Cognitum Seed BOM is 9-15 USD. The 4->5 anchor jump buys +10.6 pp coverage; the 5->6 jump buys only +3.2 pp for the same cost. Consumer recommendation: 5 anchors. Commercial / medical: 6. Convenient numerology: N=5 simultaneously satisfies three other constraints: 1. R7 multi-link mincut: needs N >= 4 for single-anchor-compromise detection 2. ADR-105 federation Krum: f=1 byzantine tolerance requires K >= 5 3. R6.2.2 coverage knee: 5 hits practical saturation These all bound by similar inverse-square-of-geometry scaling, so the alignment is not coincidental. ADR-029 (multistatic) didn't specify anchor counts; R6.2.2 fills that gap with a benchmark-backed number. Honest scope: single 5x5m geometry tested, 2D still (R6.2.1 = 3D not yet built), free-space (multipath adds +5-15% beyond Fresnel), greedy with 8 restarts approximates global optimum to 1-2 pp. Composes with: - R6/R6.2 (direct generalisation) - R7 (mincut needs N>=4) - R1 (placement x precision = full geometry budget) - ADR-029 (architectural recommendation now has a number) - ADR-105 (Krum bound matches) - R10, R11, R14 (other geometries / use cases) Coordination: ticks/tick-17.md, no PROGRESS.md edit. |
||
|
rUv
|
719875ea1d |
research(R6.2): Fresnel-aware antenna placement — 93x sensing-coverage lift from physics alone (#719)
First deferred follow-up from R6. Productises R6's Fresnel forward model into a 2D placement-search CLI: given a room + target occupancy zones, recommend Tx/Rx positions that maximise first-Fresnel coverage. Benchmark on 5x5 m bedroom (bed 3 m^2 + chair 0.64 m^2, 2900 pairs evaluated at 2.4 GHz): - OPTIMAL: 51.1% coverage (Tx 1.25,0; Rx 4.75,5; diagonal 6.10 m link) - MEDIAN: 0.5% coverage - WORST: 0.0% coverage - 93x improvement, median to optimal Counter-intuitive insight: longer links cover MORE space. Fresnel envelope width = sqrt(d * lambda) / 2 grows with link length, so the 6.10 m diagonal beats wall-parallel 5.00 m links. Up to the R10 link-budget gate. Per-cog deployment recommendations: - cog-person-count: diagonal across longest axis - cog-pose: zone inside ~50% midpoint envelope - AETHER re-ID: Tx near doorway, Rx diagonal - cog-maritime-watch: vertical diagonal through cabin - cog-wildlife (future): Tx/Rx opposite trees, threading clearing midline Improvements come from physics, not algorithms - no model retraining needed. Existing customers can re-mount seeds today for 10-100x better sensing. Honest scope: 2D approximation, free-space, rectangular zones, single-pair only, perimeter-only candidates, no link-budget gate. CLI shape ready for productisation as 'wifi-densepose plan-antennas'. Also surfaces as a deferred MCP tool 'ruview_placement_recommend'. Composes with: - R6 (direct 2D extension) - R1 (placement x precision = full geometry budget) - R10 (sets the link-budget gate this ignores) - R11 (same recipe in steel cabins) - R14 (determines whether V1/V2/V3 see the right occupant) - ADR-105 (better placement = faster epsilon convergence) Next R6.2 follow-ups catalogued: R6.2.1 (3D), R6.2.2 (N-anchor union), R6.2.3 (pose-trajectory target zones). Coordination: ticks/tick-16.md, no PROGRESS.md edit. |
||
|
rUv
|
db64b4c671 |
research(R3): cross-room re-ID — MERIDIAN closes the env-shift gap + 4 privacy constraints (#715)
Synthesis of AETHER (ADR-024) + MERIDIAN (ADR-027) + privacy framing + identified next research lever (physics-informed env prediction). Simulation results (10 subjects, 3 rooms, 128-dim embeddings, env/person scale ratio 4.7x): | Configuration | 1-shot acc | |------------------------------------------|-----------:| | Within-room (matches AETHER ~95% target) | 100% | | Cross-room, raw cosine K-NN | 70% | | Cross-room, MERIDIAN 100% env removal | 100% | | Cross-room, MERIDIAN 70% env removal | 100% | | Chance | 10% | The 30 pp gap from within-room to raw cross-room is the angular contribution of env-shift that cosine similarity can't normalise away. MERIDIAN per-room centroid subtraction recovers it -- robust even at 70% effectiveness (realistic for limited labelled examples). Privacy framing: R14 baseline + 4 new constraints specific to biometric-class re-ID data: 1. No cross-installation linkage 2. Embedding storage requires explicit opt-in (biometric consent class) 3. Cryptographically verifiable forgetting 4. No re-ID across legal entities These rule out cross-building tracking, mass surveillance, long-term unlabelled storage, third-party sharing. They allow per-installation personalisation, household anomaly detection, multi-person pose association in the same room. R3 closes the loop on R14's empathic-appliance vision: re-ID is THE primitive that makes per-occupant features possible. Without R3, R14's verticals can't ship. Identifies next research lever: physics-informed env_sig prediction from R6's forward operator + room map = zero-shot cross-room transfer without labelled examples in the new room. Composes: - R5/R6: person+env decomposition in embedding space - R7: mincut = defence against re-ID spoofing - R9: RSSI K-NN showed env-locality dominance for the K-NN primitive - R14: 4 new constraints extend R14's framework to biometric class Honest scope: additive decomposition is first-order; real CSI env effects are multiplicative in subcarrier domain. Adversarial scenarios not simulated. Coordination: ticks/tick-12.md, no PROGRESS.md edit. |
||
|
rUv
|
bcfdf0a4d0 |
research(R13): NEGATIVE — contactless BP from CSI is physically inferior to a cuff (#713)
Critical-physics scrutiny of published 'contactless BP from WiFi CSI' claims (Yang 2022, Liu 2021, others). Four physics floors quantified; all four make CSI-based BP provably worse than a 20 dollar arm cuff. 1. PTT temporal resolution: need 0.5 ms for 1 mmHg precision; ESP32-S3 maxes at 1 ms (1000 Hz CSI) and typical deployment is 10 ms (100 Hz) = 20 mmHg precision floor. Achievable but requires sacrificing every other sensing pipeline. 2. Spatial separation: carotid-femoral distance 55 cm, Fresnel envelope at 5 m link is 40 cm. Single-link CSI cannot resolve the two sites independently. Multistatic with 4-6 anchors is severely ill-posed (same regime that defeated R12). 3. Pulse-contour SNR: pulse motion at chest is 0.3 mm; breathing is 8 mm (27x larger). After 4th-order bandpass we get +20 dB HR-band SNR; literature (Mukkamala 2015) says +25 dB minimum for waveform- shape recovery. **5 dB short.** 4. Vs 0 arm cuff: best published CSI BP is +/-10 mmHg with per-subject calibration; arm cuff is +/-2 mmHg uncalibrated. CSI is 5x worse AND requires calibration the user doesn't otherwise need. Verdict: do not ship BP as a primary RuView feature. The breathing/HR features we already ship work because their motion amplitudes are 30-100x larger than the pulse waveform. Adding BP would force 1 kHz CSI rate (degrading every other pipeline), require per-subject calibration (defeating no-setup story), and ship a feature that's worse than a 20 dollar device the user can buy. Three niche scenarios remain open: - Single-subject trend monitoring (relative not absolute) - Bed-instrumented controlled-still subject (25+ dB achievable) - Multistatic PWV with 6+ anchors + per-installation calibration The general 'BP from a 9 dollar ESP32 in the corner' claim does not close. Composes: - R1 (CRLB) confirms temporal-resolution floor for PTT - R6 (Fresnel) provides the spatial floor that defeats two-site PTT - R5 (saliency) explains why whole-chest observable but 0.3 mm pulse not - R12 = loop's other negative result, same failure pattern - R14's assumption (no BP) is now empirically validated Two negative results in this loop (R12, R13) prevent the field from biasing toward overclaiming. This is the most valuable kind of tick because it marks BP-from-CSI as off-roadmap with explicit numbers, so future contributors don't waste cycles attempting it. Coordination: ticks/tick-11.md, no PROGRESS.md edit. |
||
|
rUv
|
4072455d1e |
research(R11): maritime sensing — through-bulkhead impossible, through-seam works (#712)
Physics scrutiny of WiFi-band maritime sensing scenarios. Steel skin depth is 3.25 um at 2.4 GHz, making bulkheads utterly opaque. Saltwater attenuation is 853 dB/m. The 'through-bulkhead WiFi radar' framing common in conservation/maritime is wrong; the actual feasible category is 'through-seam' sensing exploiting slot diffraction through gaskets, hatch seals, and vent grilles. Composite link budget for 7 maritime scenarios (ESP32-S3 121 dB budget, 10 dB SNR margin): FEASIBLE: - Man-overboard surface @ 200 m: +25 dB - Cabin door, 2 mm seam: +31 dB - Cabin door, 5 mm seam: +39 dB - Container, 30 mm vent slot: +45 dB IMPOSSIBLE: - Closed 10 mm steel door: -938 dB - Submarine pressure hull: -929 dB - Head 30 cm underwater: -231 dB Five feasible verticals catalogued: man-overboard surface, through-seam crew vitals, container tamper detection, hatch-seal predictive maintenance, engine-room thermal anomaly via condensation. Composes with prior threads: - R6 Fresnel envelope + slot diffraction = narrower composite envelope - R10 link-budget primitives reused unmodified for air-side maritime - R7 multi-link consistency essential against superstructure jammers - R14 privacy framework transfers directly to crew-cabin monitoring Honest scope: best-case ignores vessel vibration (5-30 Hz, in-band with R10 gait frequencies), engine ignition noise, salt-spray, steel-surface multipath. Maritime gait-classification is harder than land. The romantic 'through-hull radar' is now explicitly debunked. The actual product roadmap is gasket-leakage sensing, surface detection, and predictive-maintenance audits. Coordination: ticks/tick-10.md, no PROGRESS.md edit. |
||
|
rUv
|
a1bbe2e8a6 |
research(R1): ToA CRLB — precision floor for WiFi multistatic localisation (#711)
Quantitative Cramer-Rao Lower Bound analysis for WiFi ranging via both Time-of-Arrival and phase-based methods, with multistatic 4-anchor position-error budget. Headline (20 MHz HT20, 20 dB SNR, 100 averaged frames): - ToA range CRLB: 4.1 cm - Phase (5 deg noise): 0.17 mm - Phase advantage: 240x (after ambiguity resolution) 4-anchor convex-hull room (GDOP 1.5): - ToA position precision: 25 cm (room-pose-quality floor) - Phase position precision: 1 mm (RTK-quality, ambiguity-resolved) This is the strongest architectural lever this loop has surfaced for ADR-029 (multistatic sensing). The current learning-based attention approach has no provable precision floor; an explicit ToA-then-phase pipeline sits within 2x of CRLB by Kay's theory. Composes cleanly with R6: - R6 gives the spatial sensitivity envelope (40 cm Fresnel at 2.4 GHz) - R1 gives the ranging precision within it (1 mm phase, 4 cm ToA averaged) - Independent, additive, together bound full multistatic geometry budget Closes a gap R10 created: foliage drops SNR, which directly worsens ToA CRLB. A 50 m foliage link at 5 dB SNR drops to ~1 m ToA precision. R10's 100 m sparse-foliage range is *detectable* not *localisable*. Honest scope: - CRLB is a lower bound; real estimators sit 1-2x above it - 5 deg phase noise assumes phase_align.rs is applied - Multipath degrades CRLB by 2-5x even with MUSIC super-resolution - Integer-ambiguity (cycle-slip) is unsolved per-subcarrier; needs multi-subcarrier wide-lane unwrap Coordination: ticks/tick-9.md, no PROGRESS.md edit. |
||
|
rUv
|
650612e5a2 |
research(R6): Fresnel-zone forward model — bedrock physics for CSI sensitivity (#710)
The workspace DSP (vital_signs, multistatic, pose_tracker, tomography) implicitly assumes a forward model that maps scatterer geometry to per-subcarrier phase shifts. Nobody had written it down. This tick makes it explicit. Closed-form first-Fresnel-zone radius + point-scatterer path-delta + per-subcarrier phase prediction over 802.11n/ac 20 MHz channels (52 subcarriers, 312.5 kHz spacing). Pure NumPy demo + JSON output for downstream consumers. Headline numbers: - 5 m link first-Fresnel radius @ midpoint: 40 cm (2.4 GHz), 27 cm (5 GHz) - Inside zone-1: phase spread <0.5 deg across 52 subcarriers (band-flat) - Outside zone-1: phase spread up to 16 deg (band-dispersed) This unifies R5 + R6: R5's experimentally measured band-spread top subcarriers is exactly what the Fresnel forward model predicts for zone-1 occupancy. Closes the loop on three earlier threads: - R7 (mincut adversarial) gets a precise definition of 'physically inconsistent' instead of a learned classifier - R10 (foliage range) needs to retract 100 m sparse estimate to ~70 m to account for Fresnel-zone obstruction - R12 (eigenshift negative result) gets its revision basis: PABS over Fresnel-grounded forward operator Honest scope: point-scatterer only, first Fresnel only, frequency-flat reflectivity, LOS-only (no multipath). The scalar version is the right first-order approximation; volume-integral / multi-zone / multipath extensions catalogued as R6.1+R6.2 follow-ups. Coordination: ticks/tick-8.md, no PROGRESS.md edit. |
||
|
ruv
|
2e742305ba |
research(R10): through-foliage wildlife sensing — physics feasibility + per-species gait taxonomy
ITU-R P.833-9 vegetation-attenuation model + ESP32-S3 link-budget solver produce bounded sensing range estimates per frequency and foliage density. Plus a biomechanics-grounded gait-frequency taxonomy spanning bears (0.5 Hz) to mice (15 Hz). Headline ranges (121 dB link budget, 10 dB SNR margin): freq sparse moderate dense 2.4 GHz 99.6 m 12.0 m 4.1 m 5 GHz 19.9 m 5.2 m 2.1 m The 2.4 GHz / sparse cell (~100 m) is the practical sweet spot — 10x camera-trap coverage, always-on rather than PIR-triggered. Honest scope called out explicitly: this is feasibility math, not field measurements. Animal cooperation, foliage flutter, regulatory limits, and BSSID-fingerprint degradation in remote forest are all real follow-up problems. Vertical applications (10-20 year horizon) catalogued: - Endangered-species population census - Wildlife corridor verification - Invasive-species early warning - Anti-poaching (human gait well-separated from wildlife) - Livestock-on-rangeland tracking - Agricultural pest control Cross-connects to: - R5 (saliency is task-specific — per-species classifier needs own saliency map, same lesson as R12) - R8 (wildlife sensing wants CSI not RSSI for per-subcarrier shape) - R9 (fingerprint K-NN primitive transfers to per-individual ID) - R7 (multi-link consistency for corridor coverage) Pure-NumPy, no framework deps. ITU model + binary search solver. Coordination: tick avoided PROGRESS.md to prevent races (horizon- tracker M3+ track concurrent at the time). Files: * examples/research-sota/r10_foliage_attenuation.py * examples/research-sota/r10_foliage_results.json * docs/research/sota-2026-05-22/R10-through-foliage-wildlife.md * docs/research/sota-2026-05-22/ticks/tick-6.md |
||
|
rUv
|
6b35896847 |
research(R12): RF weather mapping eigenshift — negative-ish, with clearly-actionable revision path (#707)
Tests the simplest possible algorithm for RF-weather change detection: SVD on per-frame CSI matrix, top-10 singular values, cosine distance between spectra over time. Hypothesis: a synthetic structural perturbation (15 percent attenuation on 3 top-saliency subcarriers) should produce a larger spectral shift than natural temporal drift from operator movement in the same recording. Result honestly: it does not. The perturbation distance (0.00024) is *smaller* than the control distance (0.00035) — signal/drift ratio 0.69x. The top-K SVD-spectrum cosine is too coarse to detect small-magnitude subcarrier-specific structural changes against an operator-noise background. Three concrete fixes identified for follow-up ticks: 1. Principal angles between subspaces (PABS), not cosine on singular values — catches subspace rotations the spectrum misses 2. Per-subcarrier residual analysis after projecting onto baseline subspace — localises the perturbation 3. Multi-day baseline — knocks down operator-noise floor by 50-100x Useful cross-validations the negative result produces: * R5 task-specific saliency (count-task) does not generalise to structure-detection saliency. Same data, different relevant features. Publishable distinction. * R12 is CSI-only territory — RSSI is the trace of the CSI covariance, so if top-10 SVD-spectrum can't see this, RSSI can't either. Bounds R8 commercial-enablement story to counting only. * R7 SVD-spectrum primitive that worked for adversarial detection fails here at lower perturbation magnitude. Sensitivity does NOT scale with subtlety — confirms the algorithm is magnitude-dominated. Long-horizon vision (building structural monitoring, earthquake drift, HVAC audits, climate-controlled-archive surveillance) preserved in the research note — the physics is right, the hardware is sufficient, the deployment story works. Just need PABS + multi-day data. Coordination note: this tick avoided PROGRESS.md edits entirely because horizon-tracker is concurrently editing it. Tick-5 summary written to ticks/tick-5.md (new self-contained convention) so the 08:00 ET final summary can consolidate without conflicts. Files: * examples/research-sota/r12_rf_weather_eigenshift.py * examples/research-sota/r12_rf_weather_results.json * docs/research/sota-2026-05-22/R12-rf-weather-mapping.md * docs/research/sota-2026-05-22/ticks/tick-5.md |
||
|
rUv
|
2783f40bd1 |
feat(tools/ruview-mcp): M2 — wire real inference via cog health (#706)
* research(R9): RSSI fingerprint K-NN — 2.18x lift (MODERATE); surfaces counting-vs-localization asymmetry Hypothesis: if temporal proximity correlates with RSSI-feature proximity in the existing single-session data, RSSI fingerprinting is viable. If K-NN of each query is random in time, RSSI sequences are too noisy for fingerprint localization. Test: 1077 samples, 20-dim RSSI proxy (band-mean across 56 subcarriers), cosine-NN with K=5, measure fraction of K-NN within plus/minus 60s of each query timestamp. Compare to random baseline. Result (honest): 5-NN within +/-60s 0.169 Random baseline 0.077 Lift over random 2.18x (verdict: MODERATE) Per-query stdev 0.183 Below the >=3x STRONG-fingerprint threshold but well above 1x random. Real signal, but weaker than R8 counting result on the same data. Important asymmetry surfaced (publishable distinction): Task RSSI vs CSI retention Verdict ------- ----- ----- Counting 94.82% (R8) RSSI works well Localization ~2x random (R9) RSSI struggles in this regime This is consistent with R5's band-spread observation: the count signal integrates across the band, but localization may require per-subcarrier shape that the band-mean discards. Three actionable explanations for the MODERATE result: 1. 20-frame windows (~2s) too short for stable fingerprint while operator moves — longer windows might lift to 3-4x. 2. Within-room fingerprint space too narrow — multi-room data would show categorical lift jump (5-10x). 3. Band-mean discards the per-subcarrier shape needed for localization. Once multi-room data lands (#645), this test should be re-run; if hypothesis (2) is right, the lift will jump categorically. Files: * examples/research-sota/r9_rssi_fingerprint_knn.py * examples/research-sota/r9_rssi_fingerprint_results.json * docs/research/sota-2026-05-22/R9-rssi-fingerprint-knn.md * docs/research/sota-2026-05-22/PROGRESS.md updated * feat(tools/ruview-mcp): M2 — wire real inference via cog health subcommand ruview_pose_infer and ruview_count_infer now run the cog binary's `health` subcommand (ADR-100 contract) which performs real Candle forward-pass inference on a synthetic CSI window and emits a structured health.ok JSON event containing backend, confidence (pose) or count/confidence/p95_range (count). The MCP tools parse this event and return typed inference results. This satisfies the ADR-104 acceptance gate: "ruview_pose_infer returns a finite output for a synthetic CSI window" when the cog binary is installed. On machines without the binary, both tools still fail-open with {ok:false, warn:true} and actionable install hints. Also updates PROGRESS.md with cross-links: R7 (Stoer-Wagner) and R8 (RSSI-only 94.82% retained) marked done with cron-originated findings distilled into the research vectors section. Co-Authored-By: claude-flow <ruv@ruv.net> |
||
|
rUv
|
bb92419ccb |
research(R7): Stoer-Wagner mincut detects adversarial CSI nodes 3/3 in synthetic (#704)
Premise: in a multi-node CSI mesh, all nodes see the same physical
scene through slightly different multipath. Their per-window CSI
vectors cluster tightly under cosine similarity. An adversarial node
(replay / shift / noise injection) sits *outside* that cluster. The
Stoer-Wagner minimum cut on the inter-node similarity graph isolates
it cleanly when the cut is sharp.
Demo synthesises 4 honest nodes (one real CSI window from the paired
data + per-node Gaussian noise 6 dB below signal) and 1 adversarial
node under three attack modes. Cosine-similarity matrix, then
Stoer-Wagner mincut, then check whether partition_B is the singleton
{4} — the adversarial node.
Attack Mincut value Partition_B Isolated?
------- ------------ ----------- ---------
replay 3.4513 {4} YES
shift 3.5724 {4} YES
noise 2.5586 {4} YES
Detection rate: 3/3 = 100%.
Architectural payoff: this is the primitive that fills the stub at
. ADR-103 v0.2.0
can wire it in directly. The mincut value also becomes a continuous
'mesh trustworthiness' metric for the cog-gateway dashboard.
Honest scope: the demo uses sloppy attackers. Adaptive attackers who
have read this note can almost certainly evade by adding calibrated
noise that keeps cosine similarity above the cluster floor. The next
research step is the Stackelberg-game extension. See the
'Honest scope of this result' section in the research note.
Connections:
* R5 — top-8 saliency subcarriers are the priority list for a
more-targeted per-subcarrier consistency check.
* R8 — same primitive likely works at lower SNR with RSSI-only
metrics; cluster structure is preserved by the band integral.
Files:
* examples/research-sota/r7_multilink_consistency.py — pure-NumPy
Stoer-Wagner mincut + synthetic-adversary harness.
* examples/research-sota/r7_multilink_consistency_results.json —
full result JSON for cross-tick reproducibility.
* docs/research/sota-2026-05-22/R7-multilink-consistency.md — note.
* docs/research/sota-2026-05-22/PROGRESS.md — updated index + Done.
|
||
|
rUv
|
d9ca9b3684 |
research(R8): RSSI-only person count retains 95% of full-CSI accuracy (#703)
Builds directly on R5's band-spread observation. If the count-task
signal is spread across the WiFi band (R5: max/mean ratio 2.85× across
56 subcarriers), then RSSI — which is the integral of |H_k|^2 across
the band — keeps most of the information. The naive prior (RSSI throws
away 98% of CSI bytes) is misleading; the relevant metric is how much
of the *signal* is in the integral, not how many bytes are in the
representation.
Tested by aggregating each existing [56 × 20] CSI window down to a
[20]-vector RSSI proxy (mean across subcarriers per frame), training a
tiny MLP (Linear 20→32→8, 656 params, 5 KB) with vanilla NumPy SGD for
200 epochs on the same random 80/20 split as cog-person-count v0.0.2.
Result:
Full CSI v0.0.2 62.3% accuracy
RSSI-only (this) 59.1% accuracy = 94.82% retained
Per-class is also markedly more *balanced* (RSSI: 59.5 / 58.6 ; full
CSI: 86.2 / 34.3) — the tiny model on a low-dim input can't cheat by
leaning on class 0 the way v0.0.2's larger model does at inference.
What this enables on a 10-year horizon: phones, laptops, smart
speakers, smart TVs, smart lights — anything with WiFi reports RSSI
and anything with a CPU can run a 656-param MLP. Person counting
becomes a federated property of any room with WiFi, not a property of
the ESP32-S3 fleet.
What this doesn't prove (called out explicitly in the research note):
- Single room, single operator, single 30-min recording
- 2-class problem (label distribution is {0, 1})
- Single random draw — needs K-fold + multi-room replication
Three follow-up experiments queued in R8-rssi-only-count.md §'What's
next on this thread':
- Multi-room replication once #645 lands
- 3-class extension (0 / 1 / 2+) — measure the info-rate cliff
- Run on a non-ESP32 RSSI source (e.g. iw event on Linux laptop)
Files:
* examples/research-sota/r8_rssi_only_count.py — pure-NumPy, no
framework deps. Trains + evals in 0.72 s on CPU.
* examples/research-sota/r8_rssi_only_results.json — full JSON dump
for cross-tick reproducibility.
* docs/research/sota-2026-05-22/R8-rssi-only-count.md — method,
measured numbers, interpretation, what doesn't work yet.
* docs/research/sota-2026-05-22/PROGRESS.md — updated index + Done
log.
Coordination note: horizon-tracker is working on tools/ruview-mcp/
+ tools/ruview-cli/ + ADR-104 — this commit deliberately stays out
of those paths.
|
||
|
rUv
|
a85d4e31e4 |
research(sota): kick off SOTA research loop + first R5 saliency measurement (#702)
Sets up docs/research/sota-2026-05-22/ as the autonomous-research output dir, with PROGRESS.md as the canonical 15-vector research agenda spanning spatial intelligence, RF features, RSSI-only, and exotic/long-horizon verticals. Cron d6e5c473 (*/10 * * * *) picks threads from this file and self-terminates at 2026-05-22 08:00 ET. First concrete contribution this tick — R5 subcarrier saliency: * examples/research-sota/r5_subcarrier_saliency.py: pure-numpy port of the count cog's Conv1d encoder + count head, computes per- subcarrier input×gradient saliency via central-difference. 128 samples × 56 subcarriers × 2 forward passes/subcarrier ≈ ~3 s on CPU, no GPU or framework dependency. * docs/research/sota-2026-05-22/R5-subcarrier-saliency.md: research note with motivation, method, novelty argument, and the first measured ranking. Top-8 subcarriers for cog-person-count v0.0.2: [41, 52, 30, 31, 10, 35, 2, 38]. Max/mean ratio 2.85x. * v2/crates/cog-person-count/cog/artifacts/saliency.json: machine- readable per-subcarrier saliency + top-K lists, so future-tick experiments (retrain at K=8/16/32) consume it without re-running. Key insight from the first measurement: top-8 saliency is *band- spread* (indices span 2-52), not concentrated. This directly raises R8's (RSSI-only) feasibility ceiling, because RSSI is a band- aggregate — it retains the integral of a band-spread signal. First- order estimate: RSSI-only should hit ~60% of full-CSI accuracy for the count task. R7 (adversarial defence) inherits a concrete defender- priority list: corroborate these 8 subcarriers across nodes. This commit is the first of many short, focused contributions over the next ~12 hours. PROGRESS.md is the canonical pointer for the next tick to pick up the next thread. |