{
  "schema": "mortal-kombat.result.v1",
  "status": "completed",
  "started_at": "2026-09-19T13:48:05.633027+00:00",
  "mode": "synthetic-fixtures",
  "task": {
    "schema": "mortal-kombat.task.v1",
    "id": "owner-and-action",
    "instructions": "Extract the owner and next action from each source. Return only a JSON object with string fields owner and action. Preserve the exact name and action wording.",
    "artifacts": [
      {
        "id": "review",
        "text": "Morgan owns this item. The next action is review the fixture.",
        "expected": {
          "owner": "Morgan",
          "action": "review the fixture"
        }
      },
      {
        "id": "release",
        "text": "Riley owns this item. The next action is check the release notes.",
        "expected": {
          "owner": "Riley",
          "action": "check the release notes"
        }
      }
    ],
    "rubric": {
      "kind": "exact_fields",
      "description": "One point per exact, case-sensitive expected field across two artifacts. Extra fields earn no points. An output that is not a JSON object disqualifies the candidate. Equal scores use candidate ID order as a deterministic tie-break.",
      "fields": [
        "owner",
        "action"
      ]
    },
    "judge": {
      "kind": "rules"
    },
    "providers": {},
    "models": [
      {
        "id": "complete-fixture",
        "provider": "fixture",
        "fixture_outputs": {
          "review": "{\"owner\": \"Morgan\", \"action\": \"review the fixture\"}",
          "release": "{\"owner\": \"Riley\", \"action\": \"check the release notes\"}"
        }
      },
      {
        "id": "missing-owner-fixture",
        "provider": "fixture",
        "fixture_outputs": {
          "review": "{\"action\": \"review the fixture\"}",
          "release": "{\"action\": \"check the release notes\"}"
        }
      },
      {
        "id": "malformed-fixture",
        "provider": "fixture",
        "fixture_outputs": {
          "review": "Morgan should review the fixture.",
          "release": "Riley should check the release notes."
        }
      }
    ],
    "max_calls": 100
  },
  "task_sha256": "28129bbae2a0f3413b26f819d4cc32b6c66fb90c84ad3ad6ee37363e498ea276",
  "plan": {
    "task_id": "owner-and-action",
    "candidate_count": 3,
    "artifact_count": 2,
    "judge": "rules",
    "network_required": false,
    "maximum_candidate_calls": 0,
    "maximum_judge_calls": 0,
    "configured_call_limit": 100,
    "task_sha256": "28129bbae2a0f3413b26f819d4cc32b6c66fb90c84ad3ad6ee37363e498ea276"
  },
  "calls": [
    {
      "sequence": 1,
      "phase": "candidate",
      "candidate_id": "complete-fixture",
      "provider": "fixture",
      "configured_model": null,
      "artifact_id": "review",
      "request_text": "Extract the owner and next action from each source. Return only a JSON object with string fields owner and action. Preserve the exact name and action wording.\n\nSource artifact:\nMorgan owns this item. The next action is review the fixture.",
      "status": "completed",
      "text": "{\"owner\": \"Morgan\", \"action\": \"review the fixture\"}",
      "usage": null,
      "cost": {
        "status": "unavailable",
        "amount": null,
        "currency": null,
        "basis": "Returned token usage and user-configured rates; estimate, not an invoice.",
        "reason": "No rates configured."
      },
      "provider_call_attempted": false,
      "usage_raw": null,
      "returned_model": null,
      "response_id": null,
      "complete": true
    },
    {
      "sequence": 2,
      "phase": "candidate",
      "candidate_id": "complete-fixture",
      "provider": "fixture",
      "configured_model": null,
      "artifact_id": "release",
      "request_text": "Extract the owner and next action from each source. Return only a JSON object with string fields owner and action. Preserve the exact name and action wording.\n\nSource artifact:\nRiley owns this item. The next action is check the release notes.",
      "status": "completed",
      "text": "{\"owner\": \"Riley\", \"action\": \"check the release notes\"}",
      "usage": null,
      "cost": {
        "status": "unavailable",
        "amount": null,
        "currency": null,
        "basis": "Returned token usage and user-configured rates; estimate, not an invoice.",
        "reason": "No rates configured."
      },
      "provider_call_attempted": false,
      "usage_raw": null,
      "returned_model": null,
      "response_id": null,
      "complete": true
    },
    {
      "sequence": 3,
      "phase": "candidate",
      "candidate_id": "malformed-fixture",
      "provider": "fixture",
      "configured_model": null,
      "artifact_id": "review",
      "request_text": "Extract the owner and next action from each source. Return only a JSON object with string fields owner and action. Preserve the exact name and action wording.\n\nSource artifact:\nMorgan owns this item. The next action is review the fixture.",
      "status": "completed",
      "text": "Morgan should review the fixture.",
      "usage": null,
      "cost": {
        "status": "unavailable",
        "amount": null,
        "currency": null,
        "basis": "Returned token usage and user-configured rates; estimate, not an invoice.",
        "reason": "No rates configured."
      },
      "provider_call_attempted": false,
      "usage_raw": null,
      "returned_model": null,
      "response_id": null,
      "complete": true
    },
    {
      "sequence": 4,
      "phase": "candidate",
      "candidate_id": "missing-owner-fixture",
      "provider": "fixture",
      "configured_model": null,
      "artifact_id": "review",
      "request_text": "Extract the owner and next action from each source. Return only a JSON object with string fields owner and action. Preserve the exact name and action wording.\n\nSource artifact:\nMorgan owns this item. The next action is review the fixture.",
      "status": "completed",
      "text": "{\"action\": \"review the fixture\"}",
      "usage": null,
      "cost": {
        "status": "unavailable",
        "amount": null,
        "currency": null,
        "basis": "Returned token usage and user-configured rates; estimate, not an invoice.",
        "reason": "No rates configured."
      },
      "provider_call_attempted": false,
      "usage_raw": null,
      "returned_model": null,
      "response_id": null,
      "complete": true
    },
    {
      "sequence": 5,
      "phase": "candidate",
      "candidate_id": "missing-owner-fixture",
      "provider": "fixture",
      "configured_model": null,
      "artifact_id": "release",
      "request_text": "Extract the owner and next action from each source. Return only a JSON object with string fields owner and action. Preserve the exact name and action wording.\n\nSource artifact:\nRiley owns this item. The next action is check the release notes.",
      "status": "completed",
      "text": "{\"action\": \"check the release notes\"}",
      "usage": null,
      "cost": {
        "status": "unavailable",
        "amount": null,
        "currency": null,
        "basis": "Returned token usage and user-configured rates; estimate, not an invoice.",
        "reason": "No rates configured."
      },
      "provider_call_attempted": false,
      "usage_raw": null,
      "returned_model": null,
      "response_id": null,
      "complete": true
    }
  ],
  "candidate_outputs": [
    {
      "candidate_id": "complete-fixture",
      "artifact_id": "review",
      "text": "{\"owner\": \"Morgan\", \"action\": \"review the fixture\"}",
      "assessment": {
        "valid_json_object": true,
        "score": 2,
        "maximum": 2,
        "checks": [
          {
            "field": "owner",
            "expected": "Morgan",
            "actual": "Morgan",
            "present": true,
            "passed": true
          },
          {
            "field": "action",
            "expected": "review the fixture",
            "actual": "review the fixture",
            "present": true,
            "passed": true
          }
        ],
        "reason": "Exact, case-sensitive field matches; extra fields do not earn points."
      }
    },
    {
      "candidate_id": "complete-fixture",
      "artifact_id": "release",
      "text": "{\"owner\": \"Riley\", \"action\": \"check the release notes\"}",
      "assessment": {
        "valid_json_object": true,
        "score": 2,
        "maximum": 2,
        "checks": [
          {
            "field": "owner",
            "expected": "Riley",
            "actual": "Riley",
            "present": true,
            "passed": true
          },
          {
            "field": "action",
            "expected": "check the release notes",
            "actual": "check the release notes",
            "present": true,
            "passed": true
          }
        ],
        "reason": "Exact, case-sensitive field matches; extra fields do not earn points."
      }
    },
    {
      "candidate_id": "malformed-fixture",
      "artifact_id": "review",
      "text": "Morgan should review the fixture.",
      "assessment": {
        "valid_json_object": false,
        "score": 0,
        "maximum": 2,
        "checks": [],
        "reason": "Output is not valid JSON."
      }
    },
    {
      "candidate_id": "missing-owner-fixture",
      "artifact_id": "review",
      "text": "{\"action\": \"review the fixture\"}",
      "assessment": {
        "valid_json_object": true,
        "score": 1,
        "maximum": 2,
        "checks": [
          {
            "field": "owner",
            "expected": "Morgan",
            "actual": null,
            "present": false,
            "passed": false
          },
          {
            "field": "action",
            "expected": "review the fixture",
            "actual": "review the fixture",
            "present": true,
            "passed": true
          }
        ],
        "reason": "Exact, case-sensitive field matches; extra fields do not earn points."
      }
    },
    {
      "candidate_id": "missing-owner-fixture",
      "artifact_id": "release",
      "text": "{\"action\": \"check the release notes\"}",
      "assessment": {
        "valid_json_object": true,
        "score": 1,
        "maximum": 2,
        "checks": [
          {
            "field": "owner",
            "expected": "Riley",
            "actual": null,
            "present": false,
            "passed": false
          },
          {
            "field": "action",
            "expected": "check the release notes",
            "actual": "check the release notes",
            "present": true,
            "passed": true
          }
        ],
        "reason": "Exact, case-sensitive field matches; extra fields do not earn points."
      }
    }
  ],
  "candidate_summaries": [
    {
      "candidate_id": "complete-fixture",
      "assessment": {
        "valid": true,
        "score": 4,
        "maximum": 4
      },
      "calls": 2,
      "failed_calls": 0
    },
    {
      "candidate_id": "missing-owner-fixture",
      "assessment": {
        "valid": true,
        "score": 2,
        "maximum": 4
      },
      "calls": 2,
      "failed_calls": 0
    },
    {
      "candidate_id": "malformed-fixture",
      "assessment": {
        "valid": false,
        "score": 0,
        "maximum": 4
      },
      "calls": 1,
      "failed_calls": 0
    }
  ],
  "decisions": [
    {
      "model_a": "missing-owner-fixture",
      "model_b": "complete-fixture",
      "winner": "model_b_better",
      "reason": "Exact-field matches: missing-owner-fixture 2/4; complete-fixture 4/4.",
      "confidence": null
    }
  ],
  "tournament": {
    "prompt_id": "owner-and-action:28129bbae2a0f3413b26f819d4cc32b6c66fb90c84ad3ad6ee37363e498ea276",
    "current_ranking": [
      {
        "rank": 1,
        "status": "Ranked",
        "provider": "fixture",
        "provider_key": "fixture",
        "model_id": "complete-fixture",
        "display_label": "complete-fixture",
        "input_cost_per_million": null,
        "output_cost_per_million": null
      },
      {
        "rank": 2,
        "status": "Ranked",
        "provider": "fixture",
        "provider_key": "fixture",
        "model_id": "missing-owner-fixture",
        "display_label": "missing-owner-fixture",
        "input_cost_per_million": null,
        "output_cost_per_million": null
      },
      {
        "rank": 3,
        "status": "Disqualified",
        "provider": "fixture",
        "provider_key": "fixture",
        "model_id": "malformed-fixture",
        "display_label": "malformed-fixture",
        "input_cost_per_million": null,
        "output_cost_per_million": null,
        "reason": "evaluation failed: ProviderFailure: Candidate output is not a JSON object; remaining artifacts for this candidate were skipped."
      }
    ],
    "battles": [
      {
        "battle_id": "battle-0001",
        "model_a": {
          "provider": "fixture",
          "provider_key": "fixture",
          "model_id": "missing-owner-fixture",
          "display_label": "missing-owner-fixture",
          "input_cost_per_million": null,
          "output_cost_per_million": null
        },
        "model_b": {
          "provider": "fixture",
          "provider_key": "fixture",
          "model_id": "complete-fixture",
          "display_label": "complete-fixture",
          "input_cost_per_million": null,
          "output_cost_per_million": null
        },
        "decision": {
          "winner": "model_b_better",
          "short_reason": "Exact-field matches: missing-owner-fixture 2/4; complete-fixture 4/4.",
          "confidence": null
        }
      }
    ],
    "cache_hits": 0,
    "evaluations": 4
  },
  "error": null,
  "cost_summary": {
    "estimated_subtotals": [],
    "calls_without_cost_estimate": 0,
    "complete_for_attempted_provider_calls": false,
    "note": "No energy/hardware/subscription costs are inferred. Subtotals omit calls whose usage or rates are unavailable."
  },
  "provider_calls_attempted": 0,
  "finished_at": "2026-09-19T13:48:05.633446+00:00"
}