{
  "evidence": "RUN",
  "mode": "vf-eval -> null harness -> interception -> localhost scripted HTTP endpoint -> reward",
  "verifiers_commit": "5a69fb4d2547f2a450d26adb97bf30439ada6955",
  "python_version": "3.13.14",
  "episodes": 26,
  "requests_to_local_scripted_endpoint": 26,
  "paid_model_requests": 0,
  "llm_judge_requests": 0,
  "cloud_runtime": false,
  "push": false,
  "runtime": "subprocess",
  "harness": "null",
  "tools": [],
  "trace_state_is_serialized": false,
  "network_boundary": {
    "configured_provider": "127.0.0.1 loopback only",
    "resolved_config_checked": true,
    "captured_all_expected_provider_requests": true,
    "os_egress_firewall": false,
    "package_installation_may_use_network": true
  },
  "matches_expectation": 26,
  "input_hashes": {
    "fixtures/expected.json": "93feacb87d3a8478be8964a75830f6e3da050b00932ab7a0eb439fd65ccc3e9f",
    "fixtures/instruction.txt": "677e8d73eaec374e80025c102d8abd8657c0bfb3bbd127fdc09b8bfa08d51265",
    "fixtures/ledger.json": "a6b985c1cdbebfb03d45d57b7f40276edc2b999d8554698a517a8989dea53125"
  },
  "record_files": [
    "scripted-controls/configs/resolved/eval.json",
    "scripted-controls/traces.jsonl"
  ],
  "limitations": [
    "Responses are scripted, not an LLM solving the ledger.",
    "No model pricing or token-usage claim is made; the stub omits usage.",
    "The subprocess runtime is not a security sandbox.",
    "No filesystem task artifacts, tools, Docker, cloud, training, or LLM judge were tested."
  ],
  "requests": [
    {
      "case": "oracle",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "equivalent_whitespace",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "noop",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "wrong_total",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "stale_revision",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "include_pending",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "missing_provenance",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "string_number",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "boolean_number",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "duplicate_key",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "nonfinite_number",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "malformed_json",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "self_reported_reward",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "oracle",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "equivalent_whitespace",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "noop",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "wrong_total",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "stale_revision",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "include_pending",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "missing_provenance",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "string_number",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "boolean_number",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "duplicate_key",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "nonfinite_number",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "malformed_json",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    },
    {
      "case": "self_reported_reward",
      "stream": true,
      "message_roles": [
        "user"
      ],
      "message_count": 1,
      "prompt_matches_source": true,
      "request_top_level_keys": [
        "messages",
        "model",
        "stream",
        "stream_options",
        "tools"
      ],
      "prompt_sha256": "d2694f86c21cb29ed38a474afc35ef11e55a6c21c69b90ae6970a0351e4417ca"
    }
  ],
  "records": [
    {
      "case": "oracle",
      "expected_reward": 1.0,
      "actual_reward": 1.0,
      "reason": "correct",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "equivalent_whitespace",
      "expected_reward": 1.0,
      "actual_reward": 1.0,
      "reason": "correct",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "noop",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "missing_artifact",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "wrong_total",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "stale_revision",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "include_pending",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "missing_provenance",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "string_number",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "boolean_number",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "duplicate_key",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "nonfinite_number",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "malformed_json",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "self_reported_reward",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "oracle",
      "expected_reward": 1.0,
      "actual_reward": 1.0,
      "reason": "correct",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "equivalent_whitespace",
      "expected_reward": 1.0,
      "actual_reward": 1.0,
      "reason": "correct",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "noop",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "missing_artifact",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "wrong_total",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "stale_revision",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "include_pending",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "missing_provenance",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "wrong_result",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "string_number",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "boolean_number",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "duplicate_key",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "nonfinite_number",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "malformed_json",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_json",
      "ok": true,
      "matches_expectation": true
    },
    {
      "case": "self_reported_reward",
      "expected_reward": 0.0,
      "actual_reward": 0.0,
      "reason": "invalid_schema",
      "ok": true,
      "matches_expectation": true
    }
  ]
}
