Mirror index /local/ai_research/benchmarks/

• .. up
• audit/ dir
• parity_logs/ dir
• rebenchmark_delta/ dir
• results/ dir
• runs/ dir
• tests/ dir
• 2026-03-09-baseline-run.log .log 260 B
• 2026-03-11-baseline-run.log .log 260 B
• ARTIFACT_CONTRACT.md .md 917 B
• artifact_contract.sh .sh 791 B
• ARTIFACT_PATH_AUDIT.md .md 5.7 KiB
• BASELINE_RESULTS.md .md 1002 B
• benchmark_contract_gate.sh .sh 7.8 KiB
• benchmark_manifest_core.json .json 924 B
• check_cycle_decision.py .py 8.6 KiB
• CLASS_TRENDS.json .json 3.2 KiB
• CLASS_TRENDS.md .md 1.8 KiB
• coverage_gap_audit.py .py 13.5 KiB
• coverage_gap_audit_parity_proof.json .json 525 B
• COVERAGE_GAP_MAP.md .md 3.4 KiB
• CYCLE_DECISION_2026-03-09-fail-intent.md .md 1.7 KiB
• CYCLE_DECISION_2026-03-09.md .md 7.6 KiB
• CYCLE_DECISION_GATE_FAIL.exit .exit 2 B
• CYCLE_DECISION_GATE_FAIL.log .log 75 B
• CYCLE_DECISION_GATE_PASS.exit .exit 2 B
• CYCLE_DECISION_GATE_PASS.log .log 75 B
• CYCLE_DECISION_TEMPLATE.md .md 2.4 KiB
• DELTA_2026-03-04.json .json 2.7 KiB
• DELTA_2026-03-04.md .md 952 B
• DELTA_2026-03-07-rebenchmark-delta.json .json 2.7 KiB
• DELTA_2026-03-07-rebenchmark-delta.md .md 969 B
• DELTA_2026-03-09-generate.log .log 64 B
• DELTA_2026-03-09.json .json 2.7 KiB
• DELTA_2026-03-09.md .md 951 B
• DELTA_2026-03-11.generate.cmd .cmd 183 B
• DELTA_2026-03-11.generate.exit .exit 1 B
• DELTA_2026-03-11.generate.help.txt .txt 40 B
• DELTA_2026-03-11.generate.log .log 302 B
• DELTA_2026-03-11.generate.turn2.log .log 40 B
• DELTA_2026-03-11.generate.turn3.log .log 348 B
• DELTA_2026-03-11.json .json 2.7 KiB
• DELTA_2026-03-11.md .md 952 B
• DELTA_2026-03-11.verify.exit .exit 1 B
• DELTA_2026-03-11.verify.log .log 782 B
• DELTA_2026-03-11.verify.turn2.log .log 40 B
• DELTA_2026-03-11.verify.turn3.log .log 765 B
• DELTA_2026-03-11_REPAIR_EVIDENCE.md .md 565 B
• entrypoint_contract.sh .sh 152 B
• entrypoint_contract_check.sh .sh 4.7 KiB
• ENTRYPOINT_MATRIX.md .md 721 B
• EXPERIMENT_001.md .md 2.0 KiB
• generate_benchmark_delta.py .py 12.5 KiB
• generate_benchmark_delta.sh .sh 152 B
• generate_class_trends.py .py 12.9 KiB
• normalize_benchmark_summary.py .py 3.6 KiB
• PIPELINE_STATE_2026-03-04.md .md 4.4 KiB
• PIPELINE_STATE_2026-03-04_refresh.md .md 4.1 KiB
• README_BENCHMARKS.md .md 1.7 KiB
• run_entrypoint_matrix.sh .sh 2.8 KiB
• smoke_delta_e2e.sh .sh 7.8 KiB
• SMOKE_DELTA_EVIDENCE.md .md 110 B
• VERIFY_2026-03-09-negative.log .log 737 B
• VERIFY_2026-03-09.log .log 537 B
• VERIFY_2026-03-11.log .log 537 B
• verify_benchmark_artifacts.sh .sh 4.3 KiB
• verify_benchmark_artifacts_wrapper.sh .sh 151 B
• verify_benchmark_parity.py .py 8.0 KiB
• verify_coverage_gap_map.sh .sh 1.6 KiB