dp-zp-agent/experiments/delivery_contract_v1
2026-11-10 08:58:38 +01:00
..
build_test.py Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00
judge_calibration.json Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00
post_test_dev.json Preserve trusted metadata scope through final answer validation 2026-11-10 08:58:38 +01:00
protocol.json Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00
review_notes.json Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00
run_validation.json Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00
test_manifest.json Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00
test_results.jsonl Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00
test_results.summary.json Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00
test.json Measure frozen delivery on 80 source-bound questions per retrieval route 2026-11-10 08:50:41 +01:00