diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-21 11:44:21 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-21 11:44:21 -0500 |
| commit | 014150378d8e8cd90c2b1a01d02a2f860379dbd5 (patch) | |
| tree | 96bc4a0921cb3f510a6a2267d3d5ff078e48afd4 /docs | |
| parent | ca209ee5df16174d2137b5d5922581fc2f6d7e88 (diff) | |
RESULT 57: 棘轮判决=纯退让跑不赢偏置驱动的下沉(阶梯131k起雪崩4个量级到bf16地板,训练死走,181k处决); 同一门下bsign零事件=下沉是偏置估计器的轨迹性质而非β政策问题; 阶梯=首个连续in-vivo天花板轨迹测量; GPU0转BP s2补诚实gap
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 19 |
1 files changed, 19 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 21661f7..d36ed9c 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -568,6 +568,25 @@ direction), not training-under-fault; wave-2 = co-training with faults injected +### RESULT 57 (2026-07-21): RATCHET VERDICT — pure retreat cannot outrun the bias-driven +sink; the staircase IS the plain-lineage ceiling trajectory, and it chases beta to the bf16 +floor. The trio closes: debiasing is the only 1.0x recipe that holds. +fw72m_ratchet (user design: halve-on-crossing only, no climb, plain estimator, res-alone gate, +guards silent): mechanically flawless — zero explosions, knocks fired exactly as designed. +Staircase: 3e-3 held to 88.4k (first knock -> 1.5e-3), held to 131.2k, then CASCADE (5 knocks +in 3.2k steps -> 4.7e-5 by 134.4k), then 2.3e-5@140k, 5.9e-6@152k, 1.8e-7@154k = sub-bf16- +cliff, training dead-walks (val 3.42 best -> 4.28 noise-walk). KILLED at 181.4k (staircase +complete; remaining steps carried no information). GPU0 -> fw72m_bp_s2 (honest-gap seed). +READING: under the SAME res-alone gate, bsign saw ZERO events in 234k while ratchet's ceiling +collapsed through 4+ decades from 131k. Same estimator-family difference as plain2-vs-bsign, +now in the adaptive-beta version: the sink is a property of the BIASED estimator's trajectory, +not of the beta policy. No beta policy — fixed (plain2), descending schedule (would-be betacos), +or measured retreat (ratchet) — survives it; removing the bias (bsign) removes the sink. +Bonus instrument value: the staircase is the first continuous in-vivo ceiling-trajectory +measurement (a plain lineage's ceiling vs step curve, free of controller-climb artifacts). +LADDER STANDS: cent 3.3318 (1.67x) | bsign 3.3349 (1.0x, zero events) | plain2 3.3437 (stall) +| ratchet 3.4200 (stall@~131k). 135M gate now = bsign_s2 confirmation only (102k/234k, clean). + ### RESULT 56 (2026-07-21): BSIGN CROWN SEALED 3.3349 — THE 1.0x-COST CROWN EXISTS; the sink is BIAS-DRIVEN (user's "no effect" bet resolved AGAINST, happily). Sign randomization alone (Scellier-Bengio random nudge sign, one flag, zero extra phases) held the corridor for |