diff options
Diffstat (limited to 'docs/campaign')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 84197bc..0da6f0f 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -582,8 +582,12 @@ direction), not training-under-fault; wave-2 = co-training with faults injected - RECIPE CONSEQUENCE: estimator upgrades (centered/centfast/centmirror) demote to cos-telemetry tools and insurance; the working recipe trends to PLAIN single-sided + ride governor = 1.0x estimator cost. 8B ledger returns to the 3.2x base. -- Full-epoch validations in flight: stage1b_plain3e3 (46k, tracking cent-full within 0.004), - stage1b_est15 (26k), stage1b_ride (LAUNCHED, GPU3 — the recipe candidate). +- Full-epoch validations: stage1b_est15 SEALED 1.2374 (+0.0063 vs BP — the beta-coupled switch + rule lands at the seed-band edge; consistent with the big-beta cluster 1.233-1.238); + stage1b_plain3e3 (46k+) and stage1b_ride (GPU3) in flight. +- beta-buyback arm LAUNCHED (qb6_b1e2: 6-bit compute quant at beta 1e-2; RESULT 30's mechanism + prediction — if the +0.035 tax shrinks, quantization noise is confirmed as a wall-1 epsilon + term purchasable with beta; control = bab_p1e2 1.2571). ### RESULT 32 (2026-07-16): CROWN RESEALED — fw72m_cent 3.3318 vs BP 3.2884: honest gap 0.043, 10x below the blown-schedule number. fw72m_cent complete: 234k steps / 1.44B FineWeb tokens, from scratch, fully BP-free, DDP 2xA6000. |