exp008 LABEL CORRECTION: band0=LOW-noise / band2=HIGH-noise (numbers unchanged; the per-band win belongs to the HIGH-noise band)

README.md

@@ -75,7 +75,7 @@ resolution) so gaps live in a narrow band — the paired design is load-bearing.
 | exp003_sigma_registers | register probe: **sigma is the ONLY live axis** — caption/type/cond all compress to ≤0; ordering prereg MISS with design consequences | **shipped (candidate, s0)** |
 | exp004_anima_relay | relays on the 2B DiT via diffusion-pipe (bf16 per dtype law) | staged |
 | exp005_sdxl_tree4a | the SDXL capacity battery (guidepost/scaffold/skeleton) | designed |
-| exp008_multiband | band-ASSIGNED experts: **mechanism certifies — 3/3 surgical band lesions (50-200x), LOW-noise expert wins its band; uniform objective doesn't pay (roles enter exp009)** | **shipped (candidate, s0; s1 running)** |
+| exp008_multiband | band-ASSIGNED experts: **mechanism certifies — 3/3 surgical band lesions (50-200x), HIGH-noise band expert wins its band (label-corrected); uniform objective doesn't pay (roles enter exp009)** | **shipped (candidate, s0; s1 running)** |
 | exp006_sd15core_relay | CORE EPRED certification: **relay beats frozen (−2.5%) and matched LoRA 2-for-2; grounding gained (+0.036) where LoRA traded it; gates GROW on the core** | **shipped (candidate, s0)** |
 | exp007_amoe_lora | AMoE v1 vs monolith falsifier: **falsifier fires — uniform pressure ⇒ flat usage, dispatch pays nothing (Tree-1b law on diffusion); machinery green; next = structural band assignment** | **shipped (candidate, s0)** |
 

exp008_multiband/README.md

@@ -16,7 +16,7 @@ certified), shared dexp006 cache, 3000 steps, pure Adam wd=0.
 
 **Results** (`results.json`):
 
-| arm | overall val | band0 (HIGH) | band1 (MID) | band2 (LOW) |
+| arm | overall val | band0 (LOW noise, s01<=.35) | band1 (MID) | band2 (HIGH noise, s01>.75) |
 |---|---|---|---|---|
 | frozen | 0.124788 | 0.256406 | 0.064227 | 0.008726 |
 | multiband3 | 0.122004 | 0.250432 | 0.063046 | **0.008534** |
@@ -25,7 +25,7 @@ certified), shared dexp006 cache, 3000 steps, pure Adam wd=0.
 | prereg | outcome |
 |---|---|
 | P1 multiband ≥ monolith overall | MISS (monolith by 0.0003) |
-| P2 own-band wins | 1/3 — the LOW-noise expert wins its band |
+| P2 own-band wins | 1/3 — the HIGH-NOISE band expert wins its band (margin ~0.06%) |
 | P3 toggle bit-exact | HIT |
 | **P4 band lesions surgical** | **HIT 3/3** — own-band damage 50–200× cross-band (band0 0.0059 vs 0.00003; band1 0.0010 vs 0.000014; band2 0.00016 vs 0.000003) |
 
@@ -35,10 +35,11 @@ program's double-dissociation batteries), and the toggle/parity laws hold.
 Under a UNIFORM objective the partition does not yet out-earn shared capacity
 (P1/P2) — consistent with exp007 (2-seed) and the text line's Law 1: the
 payer must be differentiated pressure, not architecture alone. The one
-per-band win is the LOW/fine-detail expert — the first data point for the
-stage's "higher-fidelity distilled expert on low noise" thesis. Measured
-band difficulty spans 30× (0.256/0.064/0.0087) — coarse-to-fine is intrinsic
-to the objective.
+per-band win is the HIGH-NOISE band expert (the diversity/blob band; tiny
+margin — that band's eps loss is near-saturated at 0.0087). Measured band difficulty spans 30x — band0/LOW-noise 0.256 (eps hard to
+infer from lightly-noised latents) down to band2/HIGH-noise 0.0087 (input
+~= eps). LABEL CORRECTION 2026-07-17: an earlier revision of this README
+inverted the band labels (numbers unchanged); corrected same-day.
 
 **Next (per the stage plan).** exp009 attaches ROLE objectives per band
 (LOW: high-frequency-weighted loss; HIGH: coarse-structure weighting; MID: