diff options
Diffstat (limited to 'docs/campaign')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 6dd93e5..4cd5f3a 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -568,6 +568,23 @@ direction), not training-under-fault; wave-2 = co-training with faults injected +### RESULT 55 (2026-07-20): SINGLE-SIDED BIAS DIRECTLY QUANTIFIED (the BBP-thread gap) — +real, linear in beta, 0.3-1% of grad norm @3e-3; PER-SAMPLE SIGN + BATCH AVERAGE = UNBIASED +(user's claim VERIFIED at zero measurable cost). +probe_bias @plain2_s35000, 16 batches, beta {3e-3,1e-2}, selfcheck 3e-9: plain rel_bias +|mean(gEP-gBP)|/|mean(gBP)|: w2_b11 0.0035->0.0114 (x3.26 ~ beta ratio 3.33, 2.7sigma over sem +0.0013->0.0042); qkv_b0 0.0106->0.0325; all four layers >sem with ~x3.1-3.4 scaling => the +Laborieux O(beta) term measured directly on a 72M transformer. PSIGN (per-sample random nudge +sign, read re-flipped): bias -> noise floor in EVERY row (w2_b11: 0.0014 vs sem 0.0014), both +betas; sem unchanged vs plain => debiasing is FREE (no extra phase, no variance penalty at B=8; +improves with B — the scale-native estimator, supersedes per-batch bsign in theory). +Batch size alone does NOT debias (bias survives expectation); it only debiases AFTER the +per-sample sign flip makes the O(beta) term batch-antisymmetric — user's "sign+大batch=无偏" +is the correct composition. PRE-REGISTERED corollary: bias is only 0.3-1%, so if the RUNNING +bsign crown fails to stop the ceiling sink (user predicts it will fail), cent's armor is NOT +debiasing — it must be a variance/geometry property of the symmetric read; new puzzle. +In flight: fw72m_bsign (GPU1/3, per-batch sign), fw72m_ratchet (GPU0 queued, halve-only). + ### RESULT 54 (2026-07-20): THE CEILING SINKS ∝1/σ² AS TRAINING SHARPENS — no fixed β survives; "fixed β never explodes" was FALSE (it STALLS: endgame skip-storm = frozen training). β must DESCEND. User caught it: "固定β永不炸个屁！你一直skip还训不训了？" — dead right. |