learn: trained classifier arm (logistic and gradient boosting on embeddings + signals, per-fold leak screening); fit-eval record

On the 501 exp-005 units, repo-held-out folds: logistic pooled within-pair AUC
0.721 vs the LLM programs 0.762 (diff -0.041, CI [-0.116, 0.032], a tie);
gradient boosting 0.597 (significantly worse). Per family all differences span
0. Implemented with Codex; fit run by the coordinator (4.2 h on the VM).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
Marius Ciepluch
2026-10-05 07:47:42 +02:00
co-authored by Claude Opus 5.5
parent d4467f4236
commit cabdf81ece
6 changed files with 7169 additions and 4 deletions
File diff suppressed because it is too large Load Diff