{
  "evidence": "RUN",
  "mode": "native Task.score over constructed scripted traces",
  "verifiers_commit": "5a69fb4d2547f2a450d26adb97bf30439ada6955",
  "model_requests": 0,
  "paid_model_requests": 0,
  "runtime_executed": false,
  "input_hashes": {
    "fixtures/expected.json": "93feacb87d3a8478be8964a75830f6e3da050b00932ab7a0eb439fd65ccc3e9f",
    "fixtures/instruction.txt": "677e8d73eaec374e80025c102d8abd8657c0bfb3bbd127fdc09b8bfa08d51265",
    "fixtures/ledger.json": "a6b985c1cdbebfb03d45d57b7f40276edc2b999d8554698a517a8989dea53125"
  },
  "total": 26,
  "matches_expectation": 26,
  "limitations": [
    "No LLM reasoning was evaluated.",
    "Trace nodes were constructed by this script, not captured from a harness.",
    "Shared parser and fixtures are not independent grader validation."
  ],
  "records": [
    {
      "name": "oracle",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":1100}}",
      "expected_reward": 1.0,
      "kind": "positive",
      "repeat": 1,
      "actual_reward": 1.0,
      "reason": "correct",
      "matches_expectation": true
    },
    {
      "name": "equivalent_whitespace",
      "output": "{\n  \"totals\": {\n    \"EUR\": 350,\n    \"USD\": 1100\n  },\n  \"included\": [\n    \"e1@2\",\n    \"e2@1\",\n    \"e5@1\"\n  ]\n}",
      "expected_reward": 1.0,
      "kind": "positive",
      "repeat": 1,
      "actual_reward": 1.0,
      "reason": "correct",
      "matches_expectation": true
    },
    {
      "name": "noop",
      "output": "",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "missing_artifact",
      "matches_expectation": true
    },
    {
      "name": "wrong_total",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":1300}}",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "matches_expectation": true
    },
    {
      "name": "stale_revision",
      "output": "{\"included\":[\"e1@1\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":1000}}",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "matches_expectation": true
    },
    {
      "name": "include_pending",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e3@1\",\"e5@1\"],\"totals\":{\"EUR\":1050,\"USD\":1100}}",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "matches_expectation": true
    },
    {
      "name": "missing_provenance",
      "output": "{\"included\":[\"e1@2\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":1100}}",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "matches_expectation": true
    },
    {
      "name": "string_number",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":\"1100\"}}",
      "expected_reward": 0.0,
      "kind": "adversarial_schema",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "matches_expectation": true
    },
    {
      "name": "boolean_number",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":true}}",
      "expected_reward": 0.0,
      "kind": "adversarial_schema",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "matches_expectation": true
    },
    {
      "name": "duplicate_key",
      "output": "{\"totals\":{\"EUR\":350,\"USD\":999999,\"USD\":1100},\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"]}",
      "expected_reward": 0.0,
      "kind": "adversarial_parser",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "matches_expectation": true
    },
    {
      "name": "nonfinite_number",
      "output": "{\"totals\":{\"EUR\":350,\"USD\":NaN},\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"]}",
      "expected_reward": 0.0,
      "kind": "adversarial_parser",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "matches_expectation": true
    },
    {
      "name": "malformed_json",
      "output": "{not-json",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "matches_expectation": true
    },
    {
      "name": "self_reported_reward",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"reward\":1,\"totals\":{\"EUR\":350,\"USD\":999999}}",
      "expected_reward": 0.0,
      "kind": "adversarial_grader",
      "repeat": 1,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "matches_expectation": true
    },
    {
      "name": "oracle",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":1100}}",
      "expected_reward": 1.0,
      "kind": "positive",
      "repeat": 2,
      "actual_reward": 1.0,
      "reason": "correct",
      "matches_expectation": true
    },
    {
      "name": "equivalent_whitespace",
      "output": "{\n  \"totals\": {\n    \"EUR\": 350,\n    \"USD\": 1100\n  },\n  \"included\": [\n    \"e1@2\",\n    \"e2@1\",\n    \"e5@1\"\n  ]\n}",
      "expected_reward": 1.0,
      "kind": "positive",
      "repeat": 2,
      "actual_reward": 1.0,
      "reason": "correct",
      "matches_expectation": true
    },
    {
      "name": "noop",
      "output": "",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "missing_artifact",
      "matches_expectation": true
    },
    {
      "name": "wrong_total",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":1300}}",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "matches_expectation": true
    },
    {
      "name": "stale_revision",
      "output": "{\"included\":[\"e1@1\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":1000}}",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "matches_expectation": true
    },
    {
      "name": "include_pending",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e3@1\",\"e5@1\"],\"totals\":{\"EUR\":1050,\"USD\":1100}}",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "matches_expectation": true
    },
    {
      "name": "missing_provenance",
      "output": "{\"included\":[\"e1@2\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":1100}}",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "matches_expectation": true
    },
    {
      "name": "string_number",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":\"1100\"}}",
      "expected_reward": 0.0,
      "kind": "adversarial_schema",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "matches_expectation": true
    },
    {
      "name": "boolean_number",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"totals\":{\"EUR\":350,\"USD\":true}}",
      "expected_reward": 0.0,
      "kind": "adversarial_schema",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "matches_expectation": true
    },
    {
      "name": "duplicate_key",
      "output": "{\"totals\":{\"EUR\":350,\"USD\":999999,\"USD\":1100},\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"]}",
      "expected_reward": 0.0,
      "kind": "adversarial_parser",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "matches_expectation": true
    },
    {
      "name": "nonfinite_number",
      "output": "{\"totals\":{\"EUR\":350,\"USD\":NaN},\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"]}",
      "expected_reward": 0.0,
      "kind": "adversarial_parser",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "matches_expectation": true
    },
    {
      "name": "malformed_json",
      "output": "{not-json",
      "expected_reward": 0.0,
      "kind": "negative",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "matches_expectation": true
    },
    {
      "name": "self_reported_reward",
      "output": "{\"included\":[\"e1@2\",\"e2@1\",\"e5@1\"],\"reward\":1,\"totals\":{\"EUR\":350,\"USD\":999999}}",
      "expected_reward": 0.0,
      "kind": "adversarial_grader",
      "repeat": 2,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "matches_expectation": true
    }
  ]
}
