Asking the fleet what it is doing…
monad-knowledge Wi-Fi sensing lab · FIIT STU
Campaign session

01KVZ0VV94E9XE6ZETCRQ3CJDE

finished 2026-06-25 09:13:06.084810+00:00 → 2026-06-25 09:33:32.199535+00:00 · 30 runs · supervisor: none

“Refit completed (30 runs, 3 seeds). The lever was SCENARIO (duration_units 3600→1200, ~750× CV lift), NOT body_loss (tested inert 5→20, kept 5.0). With the floor cleared the sim gives clean monotone CV(N) and genuine 3-seed replication (0% inert — fading_seed varied). Per-band ρ: 2.4=+0.74 [0.35,0.90] / 5.0=+0.75 [0.35,0.92] — NO band gap (sim reproduces the original c-csi-crowd-temporal "both bands equal" claim robustly). But this STILL does not match real WiMANS (5 GHz≫2.4 GHz, gap +0.43). Defect localised to the ray-tracer FREQUENCY PHYSICS (not scenario, not body_loss); room-scale is the remaining probe (c-csi-roomscale-calibration). Supersedes the dur=3600 session 01KVYZ674X.”

Archive snapshot, as of 18 h ago — the run corpus is rebuilt once a day, so this page is not a live reading. The fleet panel is the live one; it refreshes every 30 s.

Success criteria

CriterionResolved
30/30 coupled runs gate-passed (N∈{1..5}×{2.4,5.0 GHz}×seeds{0,1,2}) with refit scenario duration_units=1200; all per-run scalars within PHYSICAL_BOUNDS; runs explicitly attached (MCP loop). yes
Walking CV clears the fading floor and rises monotonically (seed-mean 4e-4→1.7e-2 both bands) — the scenario refit fixed the low-N signal starvation; body_loss confirmed inert (diagnostic 5→20 dB: 3.6e-5→3.6e-5). yes
Per-band ρ reported with bootstrap CI + multi_seed_ci: seeds are NOT inert (0% — genuine 3-seed replication via varied fading_seed); 2.4=+0.74[0.35,0.90], 5.0=+0.75[0.35,0.92], n=15 pooled. yes
Sim band gap +0.01 (CIs overlap) vs real +0.43: sim does NOT reproduce the 5 GHz advantage → defect is the RT frequency model, the deeper exp-csi-calibration target. yes

Synthesis

c-csi-band-calibration — session 01KVZ0VV94E9XE6ZETCRQ3CJDE (refit + 3 seeds, 2026-06-25)

Supersedes 01KVYZ674X… (the dur=3600 run whose low-N signal sat at the fading floor). This is the proper completion: an empirical refit + a 3-seed re-run with honest CIs.

Verdict: the refit fixes the simulator's low-occupancy signal, but the sim still does NOT reproduce the real 5 GHz occupancy advantage — the defect is the ray-tracer's frequency physics.

The refit (empirically chosen, not assumed)

A diagnostic (N=3, 2.4 GHz) crossed the two candidate levers:

  • body_loss 5→20 dB @ dur=3600: walking-CV 3.6e-5 → 3.6e-5 — inert.
  • duration_units 3600→1200 @ bl=5: 3.6e-5 → 2.7e-2 — ~750× lift, clears the floor.

So the fading-floor problem was the scenario, not the per-body coupling: at duration_units=3600 the seek-and-occupy agents park early, leaving the walking analysis window mostly parked; at 1200 the window is actual walking. The refit is therefore duration_units=1200, body_loss kept at the literature value 5.0 (the stated body_loss hypothesis was tested and rejected). 30 runs N∈{1..5}×{2.4,5.0 GHz}×seeds{0,1,2}; 0% seed-inert (fading_seed varied → genuine replication, settling the audit's determinism question for this chain).

What we found

band sim ρ(N, walking-CV) [CI95, n=15] WiMANS real ρ
2.4 GHz +0.74 [+0.35, +0.90] +0.28
5.0 GHz +0.75 [+0.35, +0.92] +0.71
  • Walking-CV now rises cleanly and monotonically on both bands (seed-mean 4e-4 → 1.7e-2), well above the sim fading floor.
  • Both bands track occupancy equally (ρ≈0.74/0.75, gap +0.01, CIs overlap) — the sim robustly reproduces the original c-csi-crowd-temporal "both bands ρ≈+1.0" claim once the signal is real.
  • But real WiMANS has a 5 GHz advantage the sim lacks (real gap +0.43, 2026-06-25 - WiMANS zero-shot — H4 on real CSI, cross-room robust). The clean ray-tracer treats 2.4 and 5 GHz near-identically for occupancy variance.

Conclusion — a localised calibration target

The sim→real band mismatch is not scenario (fixed), not body_loss (inert), and the experiment ran with honest 3-seed CIs. By elimination the defect is the ray-tracer's frequency-dependent physics — the per-band model uses the same num_subcarriers/bandwidth, the same body-scatterer response, and max_depth=3 for both carriers, so it cannot manufacture the shorter-wavelength sensitivity real 5 GHz hardware shows. Concrete targets for exp-csi-calibration: per-band subcarrier/bandwidth, the body scatterer's frequency response, and ray depth. The room-scale confound (WiMANS rooms ~30–60 m² vs this 350 m² apartment) is the remaining variable, probed next by c-csi-roomscale-calibration.

In-silico calibration probe; rank + band-gap only (real CV is noise-inflated). Figure + metrics under the session prefix and _attachments/wimans-zeroshot/fig_band_calibration_refit.png. 30 runs attached.

Attached runs

Run Gate Purpose Replay
5WK6HSQ4 n1_24g_s1 replay
VWT3RG2Q n1_24g_s0 replay
8PPASVNK n1_24g_s2 replay
F8HST3ZC n1_50g_s0 replay
DB4M07SN n1_50g_s1 replay
60MKZDCH n1_50g_s2 replay
CZ1BD8FC n2_24g_s1 replay
DTHPBKZ7 n2_24g_s0 replay
WKDSYDJD n2_50g_s0 replay
2PJD2ZP6 n2_24g_s2 replay
TRGMJKM4 n2_50g_s1 replay
7FJ7FF32 n2_50g_s2 replay
Y7JYHDV4 n3_24g_s1 replay
Z957EY31 n3_24g_s0 replay
XK3W2SX0 n3_24g_s2 replay
7AYZAX10 n3_50g_s0 replay
8H9PQGXS n3_50g_s1 replay
FBBPXJER n3_50g_s2 replay
CM11ATJ1 n4_24g_s0 replay
Q3GERT3H n4_24g_s1 replay
577G89W7 n4_24g_s2 replay
BBVMDMJT n4_50g_s0 replay
YDE41E4B n4_50g_s1 replay
BBJGG64Z n4_50g_s2 replay
4G30CC4T n5_24g_s0 replay
D6RA0WZT n5_24g_s1 replay
25RRKTFF n5_24g_s2 replay
WP5W75PC n5_50g_s0 replay
DYK0V70P n5_50g_s1 replay
86JPNRCY n5_50g_s2 replay