summaryrefslogtreecommitdiff
path: root/docs/campaign
diff options
context:
space:
mode:
Diffstat (limited to 'docs/campaign')
-rw-r--r--docs/campaign/CASCADE_ABLATION_PLAN.md16
1 files changed, 16 insertions, 0 deletions
diff --git a/docs/campaign/CASCADE_ABLATION_PLAN.md b/docs/campaign/CASCADE_ABLATION_PLAN.md
index 931bee7..adbcaca 100644
--- a/docs/campaign/CASCADE_ABLATION_PLAN.md
+++ b/docs/campaign/CASCADE_ABLATION_PLAN.md
@@ -1878,3 +1878,19 @@ quantization (wall-1: beta-displacement below bf16 resolution) — exactly as di
- Cost consequence: COST_MODEL.md v2.1 (sourced July-2026 prices: market H100 $1.87-2.99/GPU.h,
AWS p5e blocks $4.97/GPU.h post-hike) — with amp measured, 3B-Chinchilla ~$40k / 7Bx20B ~$30k
on AWS blocks: BOTH inside the $50k envelope individually. amp is the Stage-2 default.
+
+## RESULT 75 (2026-07-30): dg128 全程验证完赛 — 口径分裂,class-2 归档
+Matched 三口径(同窗 434-440k, n=61/臂):
+| 臂 | best | 尾窗中位 |
+|---|---|---|
+| dg128 (250k 起治疗) | 3.1387 | 3.3380 |
+| bsign 未治疗 | 3.3839 | 3.5649 |
+| BP twin | 3.0902 | 3.2051 |
+- best 口径: gap +0.049, 回 72M 带(+0.076)以内, 关闭 84%; **尾窗口径: gap +0.133, 未回带, 关闭 63%**。
+ 规范裁决用尾窗; best 是噪声评估的下探偏置(三臂都低 0.11-0.18, 含 BP → 口径病不是臂病)。
+- 仪器 97% vs 全程 63% 的差值解释候选: (a) **续跑只治后 190k 步** — 前 250k 未治疗欠账已烙进权重
+ (dg128 resumed from untreated s250000, 探索性设计的固有混杂); (b) 剂量需求随走廊下沉增长, 6k 仪
+ 器段低估长程需求。谱仪轨迹轴 (c768f23 vs c768f91) 直接裁决 (b); 裁 (a) 需 from-scratch treated 臂
+ (~22h×3GPU, 等 geo 电池 + 谱仪结果再决定是否值得)。
+- 稳定性结论无保留: ×128 位移 190k 步零发散(drift 稳 0.008), 大位移在完整训练尺度安全。
+- 按 07-29 条令: class-2 exploratory, 不入 scaling 曲线; 价值 = "泄漏在全程可部分赎回" + 稳定性 + 上述口径教训。