From 937a6a65c5a6475d0992e72a684f9fbfd800f2aa Mon Sep 17 00:00:00 2001 From: Claude Date: Tue, 17 Nov 2026 08:44:54 +0000 Subject: [PATCH] research-tree: E1 coverage park, E1b opened, B14 per-part cap Co-Authored-By: Claude Opus 5.5 --- docs/claude/research-tree.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/claude/research-tree.md b/docs/claude/research-tree.md index 72c386f22..2293ef415 100644 --- a/docs/claude/research-tree.md +++ b/docs/claude/research-tree.md @@ -32,6 +32,7 @@ Rules: | P3 | O1 with size-matched K = 8 partitions | — | — | PRUNED (eligibility 23 %; lesson: control cut area as a covariate, do not match it) | Log (newest first): +- 2026-11-17: **B13-E1 PARK_G_COVERAGE** (no fit and no score). The fold-1 test (31/41 components = .756) and fold-3 learning (101/128 = .789) roles fell below the 80 % complete-component gate. This is not a performance failure and not a five-fold confirmation. **B13-E1b** (separately named) is opened: the same frozen recipe on all 552 parts, with native NaN for the two G columns where G is invalid (the fold-0 B13 recipe already kept its 4 G-invalid parts this way), no coverage gate, and the same decision rule. A deployed surrogate must score every new part. The E1 PARK receipt stays. B14 per-part cap raised to 300 s, with one rerun for indices 16, 21 and 22. - 2026-11-17: **Rulings (Claude).** - **B13-E1:** scored on each fold's *test* (552 / 204, each component once), not on validation. Validation overlaps across folds (507 evaluations over 117 components) and fold-0 validation was the screening data. A's hashed test predictions are reused; the fold-0 model is reused; only folds 1–4 are new fits. Gate: pooled field upper bound < 0. Cap 10,800 CPU-s, ≤ 4 workers. - **B13-E2:** spec accepted (MoldAstra, Drive 1rwDjGi…, SHA 182e0312) with three amendments: E1's test roles; the deployment decision is raw full-roster T−G under the B12/B13 rule, and adjusted T−G / T−C only label the mechanism; cap 14,400 CPU-s. Starts only if E1 confirms.