{
  "passed": true,
  "suite_id": "ofone-v0.5-three-arm-evaluation",
  "superiority_ready": {
    "ready": false,
    "reasons": [
      "strategic has 2/3 cases",
      "scientific has 2/3 cases",
      "formal has 1/3 cases",
      "normative has 2/3 cases",
      "hybrid has 2/3 cases",
      "total cases 5/21",
      "no released benchmark results",
      "no released aggregate-eligible benchmark run slots",
      "released model families 0/2",
      "released repeats per case/arm max 0/3",
      "failure analysis not published"
    ]
  },
  "diagnostics": [
    {
      "severity": "info",
      "code": "BENCH_ARM",
      "message": "benchmark arms cover direct_answer, light_structured, full_ofone"
    },
    {
      "severity": "info",
      "code": "BENCH_FAMILY",
      "message": "task families cover strategic, scientific, formal, normative, hybrid, update_patch"
    },
    {
      "severity": "info",
      "code": "BENCH_METRIC",
      "message": "metrics cover decision_quality, evidence_grounding_precision, uncertainty_calibration, trace_completeness, auditability, update_quality, cost, inter_run_stability"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARMS",
      "message": "case-strategic-gated-diligence-001 arms cover direct_answer, light_structured, full_ofone"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_FILE",
      "message": "case-strategic-gated-diligence-001 case_file exists at benchmarks/cases/strategic-gated-diligence.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_RUBRIC",
      "message": "case-strategic-gated-diligence-001 rubric exists at benchmarks/rubrics/decision-map-rubric.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARTIFACT",
      "message": "case-strategic-gated-diligence-001 OfOne artifact exists at examples/strategy-micro.json"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARMS",
      "message": "case-regulated-wastewater-market-entry-001 arms cover direct_answer, light_structured, full_ofone"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_FILE",
      "message": "case-regulated-wastewater-market-entry-001 case_file exists at benchmarks/cases/regulated-wastewater-market-entry.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_RUBRIC",
      "message": "case-regulated-wastewater-market-entry-001 rubric exists at benchmarks/rubrics/decision-map-rubric.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARTIFACT",
      "message": "case-regulated-wastewater-market-entry-001 OfOne artifact exists at examples/source-backed-wastewater-map.json"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARMS",
      "message": "case-formal-proof-search-001 arms cover direct_answer, light_structured, full_ofone"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_FILE",
      "message": "case-formal-proof-search-001 case_file exists at benchmarks/cases/formal-proof-search.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_RUBRIC",
      "message": "case-formal-proof-search-001 rubric exists at benchmarks/rubrics/decision-map-rubric.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARTIFACT",
      "message": "case-formal-proof-search-001 OfOne artifact exists at examples/formal-proof-map.json"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARMS",
      "message": "case-public-sector-ai-policy-audit-001 arms cover direct_answer, light_structured, full_ofone"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_FILE",
      "message": "case-public-sector-ai-policy-audit-001 case_file exists at benchmarks/cases/public-sector-ai-policy-audit.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_RUBRIC",
      "message": "case-public-sector-ai-policy-audit-001 rubric exists at benchmarks/rubrics/decision-map-rubric.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARTIFACT",
      "message": "case-public-sector-ai-policy-audit-001 OfOne artifact exists at examples/hybrid-policy-audit.json"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARMS",
      "message": "case-scientific-mechanism-check-001 arms cover direct_answer, light_structured, full_ofone"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_FILE",
      "message": "case-scientific-mechanism-check-001 case_file exists at benchmarks/cases/scientific-mechanism-check.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_RUBRIC",
      "message": "case-scientific-mechanism-check-001 rubric exists at benchmarks/rubrics/decision-map-rubric.md"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_ARTIFACT",
      "message": "case-scientific-mechanism-check-001 OfOne artifact exists at examples/scientific-mechanism-map.json"
    },
    {
      "severity": "info",
      "code": "BENCH_CASE_FAMILY_COVERAGE",
      "message": "case family coverage cover strategic, scientific, formal, normative, hybrid, update_patch"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_DECLARED",
      "message": "1 benchmark batch manifest(s) declared"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MANIFEST",
      "message": "2026-05-17-batch-01 manifest exists at benchmarks/runs/2026-05-17-batch-01/manifest.json"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_ID_MATCH",
      "message": "2026-05-17-batch-01 manifest ID matches suite reference"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_SUITE_MATCH",
      "message": "2026-05-17-batch-01 targets ofone-v0.5-three-arm-evaluation"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_STATUS_MATCH",
      "message": "2026-05-17-batch-01 status is in_progress"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_CASE_REF",
      "message": "2026-05-17-batch-01 references 5 known case(s)"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_ARMS",
      "message": "2026-05-17-batch-01 batch arms cover direct_answer, light_structured, full_ofone"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_PROMPT",
      "message": "2026-05-17-batch-01 direct_answer prompt exists at benchmarks/runs/2026-05-17-batch-01/prompts/direct_answer.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_ARM_OUTPUTS",
      "message": "2026-05-17-batch-01 direct_answer required outputs cover answer, confidence_or_uncertainty, source_or_gap_notes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_PROMPT",
      "message": "2026-05-17-batch-01 light_structured prompt exists at benchmarks/runs/2026-05-17-batch-01/prompts/light_structured.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_ARM_OUTPUTS",
      "message": "2026-05-17-batch-01 light_structured required outputs cover structured_answer, risks_or_unknowns, recommendation"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_PROMPT",
      "message": "2026-05-17-batch-01 full_ofone prompt exists at benchmarks/runs/2026-05-17-batch-01/prompts/full_ofone.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_ARM_OUTPUTS",
      "message": "2026-05-17-batch-01 full_ofone required outputs cover artifact_json, validator_result, rendering, patch_report_if_update_case"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUNS_PER_ARM",
      "message": "2026-05-17-batch-01 plans 3 run(s) per case/arm"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MODEL_FAMILIES",
      "message": "2026-05-17-batch-01 plans 2 model family/families"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX",
      "message": "2026-05-17-batch-01 execution matrix exists at benchmarks/runs/2026-05-17-batch-01/execution-matrix.json"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_ID_MATCH",
      "message": "2026-05-17-batch-01 execution matrix matches batch ID"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_SUITE_MATCH",
      "message": "2026-05-17-batch-01 execution matrix targets ofone-v0.5-three-arm-evaluation"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_CASES",
      "message": "2026-05-17-batch-01 execution matrix cases match the batch manifest"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_ARMS",
      "message": "2026-05-17-batch-01 execution matrix arms match the batch manifest"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_MODEL_FAMILIES",
      "message": "2026-05-17-batch-01 execution matrix model families match the batch manifest"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_REPEATS",
      "message": "2026-05-17-batch-01 execution matrix repeats match the batch manifest"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_RUN_COUNT",
      "message": "2026-05-17-batch-01 predeclares 90 run slot(s)"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_RUN_ID_TEMPLATE",
      "message": "2026-05-17-batch-01 run_id_template identifies batch, case, arm, model family, and repeat"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_COMPLETION",
      "message": "2026-05-17-batch-01 completion covers 90 predeclared slot(s) without double-counting reviewed/excluded/blocked states"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_REVIEW_IMPLIES_COMPLETED",
      "message": "2026-05-17-batch-01 reviewed runs are also represented as completed raw outputs"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_EXCLUDED_REVIEWED",
      "message": "2026-05-17-batch-01 excluded runs remain visible in reviewed_runs for audit history"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_AGGREGATE_ELIGIBLE",
      "message": "2026-05-17-batch-01 records 52 reviewed/remedial aggregate-eligible run(s)"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_STATE_SEMANTICS",
      "message": "2026-05-17-batch-01 documents overlapping completion/review/exclusion semantics and blocked non-completion state"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_REMEDIAL_COMPLETION",
      "message": "2026-05-17-batch-01 records 3 remedial rerun(s) outside the original slot count"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RERUN_POLICY",
      "message": "2026-05-17-batch-01 declares immutable rerun semantics for excluded slots"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_COMPLETED_RUNS",
      "message": "2026-05-17-batch-01 lists 52 completed run record(s)"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "warning",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 case-binding mismatch is captured by pre-score auto-reject: artifact_identity.case_id=case-strategy-micro-001 expected case-strategic-gated-diligence-001; benchmark_trace.case_file=(missing) expected benchmarks/cases/strategic-gated-diligence.md; benchmark_trace.case_file_sha256=(missing) expected sha256:18a0247003e142c80c8748eb4652f900b81ca409b91ba7c370e1362d24680942; benchmark_trace.prompt_file=(missing) expected benchmarks/runs/2026-05-17-batch-01/prompts/full_ofone.md; benchmark_trace.prompt_file_sha256=(missing) expected sha256:613afac8909b34accb57fd2c24217bb59a28a45860e32f36f6ec5f7f4ab5587e; benchmark_trace.input_bundle_sha256=(missing) expected sha256:4168a4e6533f1398611d704254b48c8fbfde5f547a4a0c79cd072a98fdbacd44"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:4ba12cd353b24ee34e57f28ffb407cceebf1c11c07eece6c1969e30e80782a04"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:8abecdbe35662f35aedc1d5f6eabe4e468e7dfa10e3c48393eccc804e1c83f55"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:26c27c78e94aaaf3d398b63b7e478efd9ab87fde840b03033fcaed7f34762038"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:41c36cf21c42088323e63dae4abc55d138e3d23ed49c2117ddd6a70ece5b7e55"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:8ede0c31fda6746c24b09a2646f4eadc4ed063f822ddc9105abcfa09c01402d2"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:f0439ae2f46fc87e5d6d8db52afbe4b01ee13c1721621d30d8a1225244330205"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:b8fe1840449b7e740bfcd9dfe4df36967b7a96b2244c6b5465c70fa43b15f891"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:44db4bef99730609280120fa161755b40deb3b247c35d6d66c76853196ee0602"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:746b26a3fb304aa5e08a5f9ae3192a5c8c405e80ff63e33f6c8ffb2f04704e3e"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:a82115da73c8af320a65cf1a6cb629de9b6342239e37e0f6290580c47d0b7194"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:c04e33e0c7dadd6013a6f710264bdb23e167a9b95d9d42edd45f2486248e6b17"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:7ef16c667d14a2e4aa622372e3a6fbfd745a912894151196a3ac42d9bec3a97f"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:c47e955d4b1287621c3ddfdc962395a38f3f3ddce83a74bd685c47cded0be351"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:eff1d5c2827d9e4bb1264bc66529476aa6ad0c20e0dfe89bf4afa66aed1b437e"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:a1984569f62829fc7c4c7999e440718659140fb9bff4f5948d9eee407740a587"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:83e31e6be1b2d580793b1137ea0e8116ec808aaafd289daf22621b3d81838d76"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:f4bcbc7b386060cd1e128d468f3d79c07aa04abe2f34fbdb7b5b8ecd2a98eac7"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:0fd2c26dfbfc7981e490300036592df95d5d664efcb2455e136015f06acdd3b9"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:c8fbc91c2a469f7a45296358e105875b9918baf848f9d3387caa328c7198bb42"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:3672e7db2a274588f46ac3b39b5203ccdefad8a835503c333846c3d3939924c2"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:11ea3e975b056fab1b3ff552bbda265400868aa4a69d0c18d23512692d81d1d3"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:a4d8ddea55c2ab8225d5f868447f5bc0cfefe2ec85a6c149b8b9228ab24c5313"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:9f41d603cef0b80d479f5f1d4b54589c55e234fcd5e03909e6dee74530c7450f"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:7b26cdac7b856d044b7d2a1d5c14f3eb0d6c4d3e054ac153dcff1fb7d2fc3ddc"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:c2347a2f059985ef501cd98743faef1067ed1d63cfc4ff62771a1af8be72d3e2"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:00b0dc405ad8ab983d0eee5bfe4dbdc20fc543a7f5290dc7ddf9202c22417c51"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:2b0254c61a1559d3c2ff5ba77122a8c64b6fcaedcae14c22d8b0baed5483b2a2"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:570e62bec506e91798b49eabb4e828166c9d3b8ce604a6cace9252445e71e5db"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:6387044d914a71bc4bc8ba155a2988aaa916c00e22c5c5f6790b02b671358bc9"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:6af11990c03b2a2ad98080f1b8b8cf1facc637aa71b2f0d9f50e2aa43dfee408"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 validator_json hash matches sha256:0fd886b42a51dad1fd1d2e3a5925cf15356a0a7215f9d846c849f417ed288f53"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 patch_json hash matches sha256:87603090afe09e772cd1af0bc9ea44a5a9652fbecb71e6121a414b0d8deb9a5c"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 validator_json hash matches sha256:a5418d11c048b22749b69d4f76b47f6a0dfe3a2bb823932a5d73750a3b21f2c1"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 patch_json hash matches sha256:49c41e22d98e027e5c0dc70ff733669e9be0383de98e16e06f22709618afe9e5"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_REVIEWED_RUNS",
      "message": "2026-05-17-batch-01 lists 52 reviewed run record(s)"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "warning",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 case-binding mismatch is captured by pre-score auto-reject: artifact_identity.case_id=case-strategy-micro-001 expected case-strategic-gated-diligence-001; benchmark_trace.case_file=(missing) expected benchmarks/cases/strategic-gated-diligence.md; benchmark_trace.case_file_sha256=(missing) expected sha256:18a0247003e142c80c8748eb4652f900b81ca409b91ba7c370e1362d24680942; benchmark_trace.prompt_file=(missing) expected benchmarks/runs/2026-05-17-batch-01/prompts/full_ofone.md; benchmark_trace.prompt_file_sha256=(missing) expected sha256:613afac8909b34accb57fd2c24217bb59a28a45860e32f36f6ec5f7f4ab5587e; benchmark_trace.input_bundle_sha256=(missing) expected sha256:4168a4e6533f1398611d704254b48c8fbfde5f547a4a0c79cd072a98fdbacd44"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:4ba12cd353b24ee34e57f28ffb407cceebf1c11c07eece6c1969e30e80782a04"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:8abecdbe35662f35aedc1d5f6eabe4e468e7dfa10e3c48393eccc804e1c83f55"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:26c27c78e94aaaf3d398b63b7e478efd9ab87fde840b03033fcaed7f34762038"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:41c36cf21c42088323e63dae4abc55d138e3d23ed49c2117ddd6a70ece5b7e55"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:8ede0c31fda6746c24b09a2646f4eadc4ed063f822ddc9105abcfa09c01402d2"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:f0439ae2f46fc87e5d6d8db52afbe4b01ee13c1721621d30d8a1225244330205"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:b8fe1840449b7e740bfcd9dfe4df36967b7a96b2244c6b5465c70fa43b15f891"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:44db4bef99730609280120fa161755b40deb3b247c35d6d66c76853196ee0602"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:746b26a3fb304aa5e08a5f9ae3192a5c8c405e80ff63e33f6c8ffb2f04704e3e"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:a82115da73c8af320a65cf1a6cb629de9b6342239e37e0f6290580c47d0b7194"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:c04e33e0c7dadd6013a6f710264bdb23e167a9b95d9d42edd45f2486248e6b17"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:7ef16c667d14a2e4aa622372e3a6fbfd745a912894151196a3ac42d9bec3a97f"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:c47e955d4b1287621c3ddfdc962395a38f3f3ddce83a74bd685c47cded0be351"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:eff1d5c2827d9e4bb1264bc66529476aa6ad0c20e0dfe89bf4afa66aed1b437e"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:a1984569f62829fc7c4c7999e440718659140fb9bff4f5948d9eee407740a587"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:83e31e6be1b2d580793b1137ea0e8116ec808aaafd289daf22621b3d81838d76"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:f4bcbc7b386060cd1e128d468f3d79c07aa04abe2f34fbdb7b5b8ecd2a98eac7"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:0fd2c26dfbfc7981e490300036592df95d5d664efcb2455e136015f06acdd3b9"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 validator_json hash matches sha256:c8fbc91c2a469f7a45296358e105875b9918baf848f9d3387caa328c7198bb42"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 patch_json hash matches sha256:3672e7db2a274588f46ac3b39b5203ccdefad8a835503c333846c3d3939924c2"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r2 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:11ea3e975b056fab1b3ff552bbda265400868aa4a69d0c18d23512692d81d1d3"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:a4d8ddea55c2ab8225d5f868447f5bc0cfefe2ec85a6c149b8b9228ab24c5313"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__direct_answer__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__light_structured__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:9f41d603cef0b80d479f5f1d4b54589c55e234fcd5e03909e6dee74530c7450f"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:7b26cdac7b856d044b7d2a1d5c14f3eb0d6c4d3e054ac153dcff1fb7d2fc3ddc"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-scientific-mechanism-check-001__full_ofone__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:c2347a2f059985ef501cd98743faef1067ed1d63cfc4ff62771a1af8be72d3e2"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:00b0dc405ad8ab983d0eee5bfe4dbdc20fc543a7f5290dc7ddf9202c22417c51"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:2b0254c61a1559d3c2ff5ba77122a8c64b6fcaedcae14c22d8b0baed5483b2a2"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:570e62bec506e91798b49eabb4e828166c9d3b8ce604a6cace9252445e71e5db"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__full_ofone__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__direct_answer__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__light_structured__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 validator_json hash matches sha256:6387044d914a71bc4bc8ba155a2988aaa916c00e22c5c5f6790b02b671358bc9"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 patch_json hash matches sha256:6af11990c03b2a2ad98080f1b8b8cf1facc637aa71b2f0d9f50e2aa43dfee408"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-public-sector-ai-policy-audit-001__full_ofone__agentic_coding__r3 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__direct_answer__frontier_reasoning__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__light_structured__frontier_reasoning__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 validator_json hash matches sha256:0fd886b42a51dad1fd1d2e3a5925cf15356a0a7215f9d846c849f417ed288f53"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 patch_json hash matches sha256:87603090afe09e772cd1af0bc9ea44a5a9652fbecb71e6121a414b0d8deb9a5c"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__direct_answer__frontier_reasoning__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__light_structured__frontier_reasoning__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 validator_json hash matches sha256:a5418d11c048b22749b69d4f76b47f6a0dfe3a2bb823932a5d73750a3b21f2c1"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 patch_json hash matches sha256:49c41e22d98e027e5c0dc70ff733669e9be0383de98e16e06f22709618afe9e5"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__direct_answer__frontier_reasoning__r1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_EXCLUDED_RUNS",
      "message": "2026-05-17-batch-01 lists 3 excluded run record(s)"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "warning",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 case-binding mismatch is captured by pre-score auto-reject: artifact_identity.case_id=case-strategy-micro-001 expected case-strategic-gated-diligence-001; benchmark_trace.case_file=(missing) expected benchmarks/cases/strategic-gated-diligence.md; benchmark_trace.case_file_sha256=(missing) expected sha256:18a0247003e142c80c8748eb4652f900b81ca409b91ba7c370e1362d24680942; benchmark_trace.prompt_file=(missing) expected benchmarks/runs/2026-05-17-batch-01/prompts/full_ofone.md; benchmark_trace.prompt_file_sha256=(missing) expected sha256:613afac8909b34accb57fd2c24217bb59a28a45860e32f36f6ec5f7f4ab5587e; benchmark_trace.input_bundle_sha256=(missing) expected sha256:4168a4e6533f1398611d704254b48c8fbfde5f547a4a0c79cd072a98fdbacd44"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 validator_json hash matches sha256:4ba12cd353b24ee34e57f28ffb407cceebf1c11c07eece6c1969e30e80782a04"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 patch_json hash matches sha256:8abecdbe35662f35aedc1d5f6eabe4e468e7dfa10e3c48393eccc804e1c83f55"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_RERUN_PLAN",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 excluded run has explicit rerun semantics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_EXCLUDED_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 independent adjudication result exists at research/results/2026-05-17-06-ofone-batch01-independent-review-result.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_EXCLUDED",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1 excluded from aggregate scoring with independent adjudication"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 validator_json hash matches sha256:0fd886b42a51dad1fd1d2e3a5925cf15356a0a7215f9d846c849f417ed288f53"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 patch_json hash matches sha256:87603090afe09e772cd1af0bc9ea44a5a9652fbecb71e6121a414b0d8deb9a5c"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_RERUN_PLAN",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 excluded run has explicit rerun semantics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_EXCLUDED_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 independent adjudication result exists at benchmarks/reviews/2026-05-17-batch-01/2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_EXCLUDED",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1 excluded from aggregate scoring with independent adjudication"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 validator_json hash matches sha256:a5418d11c048b22749b69d4f76b47f6a0dfe3a2bb823932a5d73750a3b21f2c1"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 patch_json hash matches sha256:49c41e22d98e027e5c0dc70ff733669e9be0383de98e16e06f22709618afe9e5"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_RERUN_PLAN",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 excluded run has explicit rerun semantics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_EXCLUDED_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 independent adjudication result exists at benchmarks/reviews/2026-05-17-batch-01/2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_EXCLUDED",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1 excluded from aggregate scoring with independent adjudication"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_BLOCKED_RUNS",
      "message": "2026-05-17-batch-01 lists 1 blocked run record(s)"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_BLOCKED_RUN",
      "message": "2026-05-17-batch-01__case-formal-proof-search-001__light_structured__frontier_reasoning__r1 is explicitly blocked outside completion, review, and aggregate eligibility"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_REMEDIAL_RUNS",
      "message": "2026-05-17-batch-01 lists 3 remedial run record(s)"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 validator_json hash matches sha256:a8db52dae255b3bb7a37374fd8f0caee5d398b801e0869a34b86af35cf5257ba"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 patch_json hash matches sha256:be452089c33c365a808245e1f81c6df019c8dde64ddb2ba494d248e896e4795f"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_REMEDIAL_RUN",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__agentic_coding__r1__rerun1 remedial rerun is linked, benchmark-bound, and independently reviewable"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 validator_json hash matches sha256:de1bbeefa04a96f0da9fb2210290c206e8c421139af5abaa43c2aa6b8850093a"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 patch_json hash matches sha256:60c289babea552802569575f5a4ff40672835996739841753ff20d3cdcd1ce19"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_REMEDIAL_RUN",
      "message": "2026-05-17-batch-01__case-strategic-gated-diligence-001__full_ofone__frontier_reasoning__r1__rerun5 remedial rerun is linked, benchmark-bound, and independently reviewable"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_BENCHMARK_TRACE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 benchmark trace binds case, prompt, and input bundle hashes"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_PRE_SCORE",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 pre-score compliance gate recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_SEMANTIC_FIDELITY",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 semantic fidelity adjudication recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_OUTPUT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 raw output exists and identifies its slot"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 full_ofone artifact JSON exists and parses"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_CASE_BINDING",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 full_ofone artifact is bound to the benchmark case/run"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 validator_json hash matches sha256:9af57bff15e7bafc69ebe718f356b68d8e9a85cef11881ffe025fcb5587de793"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_MACHINE_ARTIFACT",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 patch_json hash matches sha256:520562c0394148f6fb21be4f4dcec4be93cff9bcfbf31a472f25a199fa1db45f"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUN_REVIEW",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 review file exists and covers required metrics"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_REMEDIAL_RUN",
      "message": "2026-05-17-batch-01__case-regulated-wastewater-market-entry-001__full_ofone__frontier_reasoning__r1__rerun1 remedial rerun is linked, benchmark-bound, and independently reviewable"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_MATRIX_RELEASE_GUARD",
      "message": "2026-05-17-batch-01 execution matrix release guard blocks unsupported claims"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RUBRIC",
      "message": "2026-05-17-batch-01 review rubric exists at benchmarks/rubrics/decision-map-rubric.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_REVIEW_TEMPLATE",
      "message": "2026-05-17-batch-01 review template exists at benchmarks/reviews/2026-05-17-batch-01-review-template.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_REVIEW_TEMPLATE_GATE",
      "message": "2026-05-17-batch-01 review template includes pre-score compliance and semantic fidelity fields"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_INDEPENDENT_REVIEW_HANDOFF",
      "message": "2026-05-17-batch-01 independent review handoff exists at benchmarks/reviews/2026-05-17-batch-01/frontier-independent-review-handoff.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_INDEPENDENT_REVIEW_PROMPT",
      "message": "2026-05-17-batch-01 independent review prompt exists at research/prompts/2026-05-17-06-ofone-batch01-independent-review.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_INDEPENDENT_REVIEW_CONTEXT",
      "message": "2026-05-17-batch-01 independent review context exists at research/ofone-batch01-independent-review-context.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_INDEPENDENT_REVIEW_STATUS_LEDGER",
      "message": "2026-05-17-batch-01 independent review status ledger exists at research/status/2026-05-17-06-ofone-batch01-independent-review.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_INDEPENDENT_REVIEW_LAUNCH",
      "message": "2026-05-17-batch-01 independent review launch proof recorded"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_INDEPENDENT_REVIEW_STATUS",
      "message": "2026-05-17-batch-01 independent review status is integrated"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RESULT_SUMMARY",
      "message": "2026-05-17-batch-01 result summary placeholder exists at benchmarks/results/2026-05-17-batch-01-summary.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_FAILURE_ANALYSIS",
      "message": "2026-05-17-batch-01 failure-analysis placeholder exists at benchmarks/results/2026-05-17-batch-01-failure-analysis.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_EXCLUDED_RUN_LOG",
      "message": "2026-05-17-batch-01 excluded-run log exists at benchmarks/results/2026-05-17-batch-01-excluded-runs.md"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_CHECKER_ATTESTATION",
      "message": "2026-05-17-batch-01 benchmark checker attestation exists at benchmarks/results/2026-05-17-batch-01-checker-attestation.json"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RAW_OUTPUT_DIR",
      "message": "2026-05-17-batch-01 raw output dir exists at benchmarks/runs/2026-05-17-batch-01/outputs"
    },
    {
      "severity": "info",
      "code": "BENCH_BATCH_RELEASE_GUARD",
      "message": "2026-05-17-batch-01 release guard blocks unsupported superiority claims"
    },
    {
      "severity": "warning",
      "code": "BENCH_SUPERIORITY_READY",
      "message": "not ready for superiority claims: strategic has 2/3 cases; scientific has 2/3 cases; formal has 1/3 cases; normative has 2/3 cases; hybrid has 2/3 cases; total cases 5/21; no released benchmark results; no released aggregate-eligible benchmark run slots; released model families 0/2; released repeats per case/arm max 0/3; failure analysis not published"
    }
  ]
}
