{
  "schema_version": 1,
  "evidence_kind": "new actual-member experiment; not historical replay",
  "date": "2026-09-21",
  "run_id": "matrix-98a78c934d",
  "verdict": "FAIL",
  "victor_commit": "09f9894072c0c9dbe67cbb5e768e86a21a17f9fa",
  "source_clean_at_launch": true,
  "harness_sha256": "167d420367ac5ed1c96b985489b7d3eddff1312e0534a0e82b1c6452cca4c697",
  "private_evidence_sha256": "9169da658909effabb037915f900296a03e422d67e394f504f73cdf6bc852b6b",
  "provider": "inferflux",
  "model": "qwen3-coder-30b",
  "case_contract_version": 2,
  "task_profile": "single-file",
  "cases": [
    {
      "case": "sequential",
      "passed": true,
      "failures": [],
      "calls": 6
    },
    {
      "case": "parallel",
      "passed": true,
      "failures": [],
      "calls": 6
    },
    {
      "case": "hierarchical",
      "passed": true,
      "failures": [],
      "calls": 6
    },
    {
      "case": "pipeline",
      "passed": true,
      "failures": [],
      "calls": 5
    },
    {
      "case": "consensus",
      "passed": true,
      "failures": [],
      "calls": 6
    },
    {
      "case": "reflection",
      "passed": true,
      "failures": [],
      "calls": 10
    },
    {
      "case": "group_chat",
      "passed": true,
      "failures": [],
      "calls": 5
    },
    {
      "case": "debate",
      "passed": false,
      "failures": [
        "member_outcomes",
        "missing_artifacts:judge",
        "conversation_contract",
        "decision_contract:FileNotFoundError"
      ],
      "calls": 13
    },
    {
      "case": "handoff",
      "passed": true,
      "failures": [],
      "calls": 4
    },
    {
      "case": "adaptive",
      "passed": true,
      "failures": [],
      "calls": 4
    },
    {
      "case": "dynamic_router",
      "passed": true,
      "failures": [],
      "calls": 2
    },
    {
      "case": "multi_level_hierarchy",
      "passed": false,
      "failures": [
        "missing_artifacts:first",
        "pytest:first",
        "semantic_oracle:first"
      ],
      "calls": 5
    },
    {
      "case": "ensemble_judge",
      "passed": true,
      "failures": [],
      "calls": 16
    },
    {
      "case": "ensemble_synthesizer",
      "passed": false,
      "failures": [
        "decision_contract:ValueError"
      ],
      "calls": 23
    },
    {
      "case": "ensemble_vote",
      "passed": true,
      "failures": [],
      "calls": 14
    }
  ],
  "calls": 125,
  "http_status_counts": {
    "200": 125
  },
  "distinct_observed_member_sessions": 33,
  "accounting_failures": [],
  "accounting_observations": 125,
  "totals": {
    "tokens_in": 449330,
    "tokens_out": 11373,
    "cache_read_tokens": 12,
    "cache_creation_tokens": 0
  },
  "buffered_gateway_deadline_seconds": 120,
  "shared_cache_cleared": false,
  "limitations": [
    "Independent numeric oracle checks a finite domain; it is not a hostile-code sandbox.",
    "Buffered calls only; no streaming or origin-cancellation acceptance.",
    "Reported cache counts do not establish backend executed reuse.",
    "Runtime identities and hardware acceptance must accompany this report.",
    "No tokenizer-equivalence or session-lease acceptance claim.",
    "Unsupported durable partial resume remains explicitly deferred.",
    "Single-file profile is distinct from standard two-file evidence; do not pool counts."
  ]
}
