research(rectification): varga-resolution M1–M3 and robustness on v5 — segment posterior, segment-aware probe order, domain-targeted vargas (BUG-1105)
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
This commit is contained in:
co-authored by
Claude Fable 5.1
parent
f798366f89
commit
52bfbb2ac5
@@ -129,3 +129,4 @@ Do not open new product surfaces before at least one of these four lanes is clos
|
||||
- 未解决的只剩「区间内部并列」,目前唯一被证明有效的信息源是用户提供的带年月新经历。
|
||||
- 2026-09-29 打分方法研究(脚手架,判定待 v5):`<repo>/docs/research/rectification_scoring_research_2026_09_29.md`——似然比校准权重 / 缺席证据 / 精度追问三条流水线已在 v4 上跑通,所有判定 `pending_v5`;任务书 `docs/tasks/TASK-rectification-scoring-research-20260929.md`,前置 `TASK-rectification-holdout-expansion-20260929.md`。
|
||||
- 2026-09-29 起评价集换 **v5**(77 例公开 AA,`references/real_case_calibration/minute_rectification_holdout_v5.json`):协议 `holdout_v5_protocol_2026_09_29.md`、构建与基线成绩单 `holdout_v5_build_2026_09_29.md`。后续打分判定以 v5 为准,v4 数字只作历史对照。
|
||||
- 2026-09-30 盘型口径研究(BUG-1105):`<repo>/docs/research/rectification_varga_resolution_2026_09_30.md`——目标从分钟改为分盘上升段。v5 六题后 ±10 D9 / D10 头段 = 真值 88% / 86%,占比 ≥ 0.6 留一法 92% / 90%;±30 约 1/4–1/3 用户可给可信分盘;±60 分盘 blocked。按段选题 ≤ ±30 有 +3~+7 例;提前停不过红线;「不用校正」只对只需 D1 的问题成立。**建议立实现单**(§7)。
|
||||
|
||||
Reference in New Issue
Block a user