diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-28 13:20:34 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-28 13:20:34 -0500 |
| commit | 98d5ea09d1498f802f2ad06f5f67b385e228f063 (patch) | |
| tree | 173821434b3d6707d319ae649e34d1f5bf83df5d /docs/campaign | |
| parent | 752e113d67e510c4152bb1f33301b1dc509322af (diff) | |
RESULT 66: head被节流到60%(位移微探针:全族1.00-1.02唯W_out 0.60) — 用户等价LR假说命中并定位到单矩阵; Adam岛m/√v节流,对centered/fp32/K8全不敏感=EP头读共享结构; --head_lr_mult实装; 电池2(headmix诊断+hlr1.67/2.5补偿)在飞
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
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 277ebf1..5c4b25c 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 66 (2026-07-28): THE HEAD IS THROTTLED TO 60% — user's equivalent-LR hypothesis +CONFIRMED and localized to ONE matrix; symmetrization/precision/depth all irrelevant to it. +Displacement micro-probe (600 steps from s250000, ||dW||/||W|| per family): every family +IDENTICAL EP-vs-BP (ratio 1.00-1.02) EXCEPT W_out: EP 0.0068 vs BP 0.0114 = 60%. Muon-managed +blocks are magnitude-immune (msign); W_out lives on the Adam island where step ~ m/sqrt(v) — +the EP head-read's per-coordinate temporal coherence is lower, v inflates ~2.8x, Adam throttles +the loss-facing matrix by 40%. Explains R44 (gap lives head-side), the anneal freeze (head +can't track features), and width-scaling (louder states -> stronger throttle). +BATTERY 1 (all closed ~0% of the 0.0685 leak): centered 0%, fp32 +3%, K8 (arm died, rerun +pending) — the throttle source is INVARIANT to estimator symmetry, precision, and relax depth: +it is the shared structure of the EP W_out read, not removable noise. (cos flat 0.986-0.988 +through the losing segment; EP gn 0.15, clip never fires — user's checklist all measured.) +FA-argument (user): static direction quality exonerated a priori — FA learns at cos 0.3. +BATTERY 2 IN FLIGHT: leak_headmix (--bpmix head = the head's share of the leak, diagnostic +ceiling), leak_hlr17 / leak_hlr25 (--head_lr_mult, the zero-cost compensation candidate). +If hlr claws back what headmix shows, the width fix is ONE hyperparameter. + ### RESULT 65 (2026-07-28): THE LEAK INSTRUMENT WORKS — first reading +0.0685/6k at the SAME state (20x the trajectory-averaged rate: front-loaded/self-adapting), screening battery 1 in flight. Paired 6k segments from fw135m_bsign_s250000: BP tail val_mean 3.4982 vs EP-plain |