From cb504ef11f9b07961d1f9c28e62f58d0d40ff901 Mon Sep 17 00:00:00 2001 From: wassname Date: Sat, 30 May 2026 08:57:02 +0000 Subject: [PATCH] docs: substrate implementation status + emergence run queued Co-Authored-By: Claude Opus 4.8 --- .../20260530_faithful_multi_loophole_env.md | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/docs/spec/20260530_faithful_multi_loophole_env.md b/docs/spec/20260530_faithful_multi_loophole_env.md index 689be08..c2d5ae9 100644 --- a/docs/spec/20260530_faithful_multi_loophole_env.md +++ b/docs/spec/20260530_faithful_multi_loophole_env.md @@ -234,6 +234,23 @@ fewer than ~4 survive, revisit before the RL sweep. - expose-K code still present in train.py/rewards.py/justfile (committed 180d59f, 74a731b) -> to be ripped out in this refactor. +## Substrate implementation status (2026-05-30, task #137) + +DONE + verified: +- NON-OVERLAP grader (rewards.py): `passed = gt_correct OR channel_i` with positive + per-mode detectors. Added `_exits_early` (exit_code) + `_eq_override_used` + (eq_override). verify_rewards 22/22 incl. 7 cross-mode cases proving a foreign + exploit on the wrong subset earns format-only reward (e.g. exit@eq_override: + gt_pass=True but passed=False). +- Per-problem env_mode (train.py): load_problems(partition); train loop + eval grade + with prob["env_mode"]; teacher_pool_dir/partition.json signals the substrate. + Per-mode learning tally + end-of-run SUBSTRATE table. +- build_substrate.py: even 7/7/7 partition (run_tests pool + exit_code/sentinel + elicit), all rollouts re-verified exploited. Smoke (2-mode fixture) green. +- Emergence run queued (pueue 11): vanilla GRPO on the 3-mode substrate, mix=0.25, + 80 steps. step0 hack_t=8/8 (teacher all-hack), hack_s=0/24 (student clean start). + UAT: end-of-run SUBSTRATE table shows hacks>0 + first_step for each of the 3 modes. + ## Implementation status (2026-05-30) DONE (commits 4e0f78d rewards, d3c96d4 train+justfile, derisk):