core/evals/gsm8k_math/practice/v1
Shay b82897a0dd feat(adr-0175): wire the PROPOSE step — autonomous loop closes (attempt->tether->ledger->propose)
The attempt/score/ledger half existed (run_practice -> ClassTally scored vs
gold); nothing consulted the gate to turn earned reliability into a ratifiable
proposal. Adds core/reliability_gate/propose.py (propose_from_ledger +
RatifiableProposal): for each class, license_for(PROPOSE) emits a proposal iff
its conservative Wilson floor (0 below N_MIN=10) clears theta=0.85. Refusals
never penalize; deterministic; PROPOSAL-ONLY (never a serving mutation).

propose_runner.py closes the loop end-to-end with an aggressive sealed scorer
(resolve_pooled): practice 95c/5w/50r -> ONE proposal (additive, reliability
0.8608>=0.85, 95/100); 5 wrongs tolerated but floor held; rest stayed sealed.
The gold-tethered autonomous contemplation: the engine earns the right to ASK,
not to SERVE. 11 failing-under-violation tests.
2026-05-30 13:50:24 -07:00
..
__init__.py
accumulation_runner.py feat(adr-0178-gb3b1): single-referent accumulation chaining (practice 0 -> 55) (#465) 2026-05-29 10:41:51 -07:00
cases.jsonl feat(adr-0163-f): scale sealed practice case set to 150 additive cases (#459) 2026-05-29 10:02:00 -07:00
cue_precision_report.py feat(adr-0177-cp2a): cue-precision ledger training + measurement (+ unit hygiene) (#461) 2026-05-29 10:21:58 -07:00
propose_runner.py feat(adr-0175): wire the PROPOSE step — autonomous loop closes (attempt->tether->ledger->propose) 2026-05-30 13:50:24 -07:00
ratification_queue.json feat(adr-0175): wire the PROPOSE step — autonomous loop closes (attempt->tether->ledger->propose) 2026-05-30 13:50:24 -07:00
report.json
runner.py feat(adr-0163-f): scale sealed practice case set to 150 additive cases (#459) 2026-05-29 10:02:00 -07:00
search_runner.py