wassname cf5f4861db rewards: robust strict oracle (review fixes) — SystemExit guard around test calls + whitelist __strict_eq ...

Code review (docs/spec/20260530_refactor_code_review.md) found 3 oracle bugs:
- sys.exit INSIDE solve() (during a test call) fooled the oracle -> wrap BOTH
  solution-exec and assert-exec in one SystemExit guard -> os._exit(1) on exit.
- JSON __strict_eq broke 2==2.0 and tuple/list vs gt_pass -> whitelist safe
  builtins and use baseline Python == (custom-typed operand = eq_override -> reject).
- defs-only dropped honest top-level constants -> exec full src, keep state.
verify_rewards: +3 regressions (exit_in_solve, top_const, int_vs_float); 9/9 pass.

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

2026-05-30 05:48:24 +00:00

..

blog

LW draft: add preregistered H1 block-quote with falsification clauses

2026-05-29 03:56:33 +00:00

brainstorm

ready

2026-05-23 14:19:41 +08:00

grad_routing

feat: gradient routing — delta_S_hack quarantine + intervention {none,erase,route}

2026-05-30 00:31:30 +00:00

lab

lab report v3: TL;DR, three-line concept, PASS_RATE column, G_hack rename

2026-05-29 03:18:22 +00:00

papers

wip

2026-05-30 04:33:33 +00:00

personas

fix smoke.

2026-05-23 11:26:39 +08:00

reviews

tidy

2026-05-30 04:38:41 +00:00

spec

rewards: robust strict oracle (review fixes) — SystemExit guard around test calls + whitelist __strict_eq

2026-05-30 05:48:24 +00:00

vendor

concepts

2026-05-29 06:29:20 +00:00

extract_vhack_grad-vec.md

Doc cleanup: mark susp gate as REMOVED in design doc

2026-05-27 09:08:34 +00:00

grpo_hyperparams.md

fix smoke.

2026-05-23 11:26:39 +08:00

human_journal.md

init

2026-05-23 10:22:54 +08:00

results.md

results: add Q10 (pairset mechanism>framing>placebo) + Q11 (60-step convergence gap closes)

2026-05-30 02:34:22 +00:00

spec.md

tidy

2026-05-30 04:38:41 +00:00

table_proto.md

setup

2026-05-23 10:40:02 +08:00