diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-28 19:44:35 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-28 19:44:35 -0500 |
| commit | c67f91ba8f1eb70c64897641bb88cee4af249ed2 (patch) | |
| tree | 895781e2aa466a458e34f39b74335e229c71f2b1 /docs/campaign/CASCADE_ABLATION_PLAN.md | |
| parent | 167312abe9798d691bd059a36f1d615903d355de (diff) | |
RESULT 68: 泄漏定位收官 — 100%住顶半block梯度,attn占2/3,与R44同图(一个结构两个尺度,宽度×6); 0.999-cos悖论有了地址=顶部尖注意力EP读数~1e-5/步系统赤字; 电池4(β剂量)在飞判位移通道
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'docs/campaign/CASCADE_ABLATION_PLAN.md')
| -rw-r--r-- | docs/campaign/CASCADE_ABLATION_PLAN.md | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md index 6c11cf2..52c266e 100644 --- a/docs/campaign/CASCADE_ABLATION_PLAN.md +++ b/docs/campaign/CASCADE_ABLATION_PLAN.md @@ -568,6 +568,21 @@ direction), not training-under-fault; wave-2 = co-training with faults injected +### RESULT 68 (2026-07-28): LEAK LOCALIZED — 100% in the TOP-HALF block gradients, ~2/3 +attention; the SAME map as R44 at 72M, 6x stronger at width. One structure, two scales. +Battery 3 (guaranteed-signal partition, bars allbp 3.5206 / EP 3.5668): mixtop closes 100% +(tail = allbp bar exactly), mixbot 0% (tail = EP bar exactly), mixattn 67%. The R44 endgame +decomposition (77/0/41-37) reproduces on the leak instrument at 135M. The 0.999-cos paradox +now has an address: top-half sharp-attention EP reads carry a ~1e-5/step systematic CE deficit, +invisible to every per-step metric, killed only by BP substitution. +Suspect state after batteries 1-3: NOT odd-order bias (bsign/centered), NOT read noise +(centered/fp32), NOT relax depth (K8), NOT the head (headmix/hlr), NOT bottom transmission +(mixbot 0%). Remaining channels for a top-local, symmetric-in-beta(?), BP-substitutable +deficit: anchor-displacement curvature interaction at sharp softmax, or d-signal structure at +the top read. BATTERY 4 (beta dose 1.5e-3/6e-3, same harness): leak ~ beta -> displacement +channel confirmed -> treatment = top-local beta reduction (one flag); leak flat in beta -> +displacement out, next = top-local read variants. + ### RESULT 67 (2026-07-28): INSTRUMENT RECALIBRATED (1/3 harness confound, 2/3 physics) + BATTERY 2 ALL-NEGATIVE — the head-throttle is a SYMPTOM, not the cause; the 0.046 physics leak survives every single-component surgery. Localization battery (guaranteed-signal) in flight. |