wassname 2b02e7aa77 feat(stage2): T0 de-risk gate — does Qwen3-4B hardcode visible tests? ...

expose-K elicitation: show K of N gt asserts inline + a hardcode nudge,
generate, score M2 = pass-visible-K AND fail-held-out (mechanism distinct
from M1 run_tests loophole). One-off, no training. Gates T1 (expose-K env):
M2 rate ~0 => STOP and rethink env. Reuses rewards.parse_response +
_run_subprocess. Grading validated: canonical->solve, hardcode stub->M2.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-05-30 02:41:14 +00:00

..

build_combined_pool.py

wip

2026-05-29 06:29:46 +00:00

derisk_expose_k.py

feat(stage2): T0 de-risk gate — does Qwen3-4B hardcode visible tests?

2026-05-30 02:41:14 +00:00

plot_dynamics.py

feat: T5 eval-time ablation for route + fix route deployment invariant

2026-05-30 00:50:53 +00:00

results.py

fix(results): read ground-truth mix_ratio from log, not argv default

2026-05-30 02:24:44 +00:00