{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:12.638108+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "tests.test_weak_fixes.test_encode_function_with_invalid_json_abi_shows_error",
      "eval.tests.test_decode_params.test_decode_params_invalid_type_fallback",
      "eval.tests.test_encode_function.test_encode_function_extra_params_ignored",
      "eval.tests.test_error_paths.test_encode_uint_overflow",
      "tests.test_decode_log.test_error_topic_wrong_length",
      "tests.test_abi_edge_cases.test_tuple_param_duplicate_type",
      "tests.test_abi_edge_cases.test_event_missing_name_field",
      "tests.test_decode_log.test_error_empty_data",
      "tests.test_abi_edge_cases.test_abi_duplicate_param_name",
      "tests.test_decode_function.test_error_file_not_found",
      "tests.test_decode_log.test_error_file_not_found",
      "tests.test_decoder_edge_cases.test_lenient_uint_with_ether_unit",
      "tests.test_decoder_edge_cases.test_lenient_int_underflow",
      "tests.test_decoder_edge_cases.test_lenient_uint_fractional_wei_rejects",
      "tests.test_encode_function.test_file_not_found_error",
      "tests.test_edge_cases.test_invalid_uint_error",
      "tests.test_encode_function.test_invalid_json_abi_file",
      "tests.test_encode_function.test_extra_parameters_ignored",
      "tests.test_encode_function.test_invalid_uint_value_not_a_number",
      "tests.test_abi_edge_cases.test_tuple_duplicate_components_field",
      "tests.test_decode_log.test_error_invalid_signature_format",
      "tests.test_abi_edge_cases.test_abi_duplicate_param_type",
      "tests.test_decoder_edge_cases.test_lenient_uint_with_gwei_unit",
      "tests.test_decoder_edge_cases.test_lenient_uint_too_many_decimal_places_ether",
      "tests.test_decoder_edge_cases.test_lenient_uint_array_with_units",
      "tests.test_encode_params_simple.test_error_type_mismatch_string_to_uint",
      "tests.test_encode_params_simple.test_error_missing_both_args",
      "tests.test_encode_params_simple.test_error_uint_negative_lenient",
      "tests.test_param_coverage.TestEdgeCases.test_array_of_array_of_tuple",
      "tests.test_param_error_paths.TestParamExpectingMethod.test_param_expects_map_not_number",
      "tests.test_param_error_paths.TestParamExpectingMethod.test_param_expects_map_not_string",
      "tests.test_param_error_paths.TestParamExpectingMethod.test_param_expects_map_not_bool",
      "tests.test_param_error_paths.TestParamExpectingMethod.test_param_expects_map_not_array",
      "tests.test_param_error_paths.TestParamExpectingMethod.test_param_expects_map_not_null",
      "tests.test_param_error_paths.TestTupleParamExpectingMethod.test_tuple_param_expects_map_not_string",
      "tests.test_param_error_paths.TestTupleParamExpectingMethod.test_tuple_param_expects_map_not_bool",
      "tests.test_abi_edge_cases.test_abi_missing_param_name",
      "tests.test_abi_edge_cases.test_tuple_missing_type_field",
      "tests.test_decode_log.test_error_wrong_param_count_in_signature",
      "tests.test_decoder_edge_cases.test_lenient_uint_with_fractional_ether",
      "tests.test_decoder_edge_cases.test_lenient_int_overflow",
      "tests.test_serde_duplicate_fields.TestParamDuplicateFields.test_duplicate_name_field_param",
      "tests.test_serde_duplicate_fields.TestParamDuplicateFields.test_duplicate_internalType_field_param",
      "tests.test_serde_duplicate_fields.TestParamDuplicateFields.test_duplicate_components_field_param",
      "tests.test_serde_duplicate_fields.TestTupleParamDuplicateFields.test_duplicate_internalType_field_tuple_param",
      "tests.test_param_error_paths.TestTupleParamExpectingMethod.test_tuple_param_expects_map_not_null",
      "tests.test_param_error_paths.TestTupleParamExpectingMethod.test_tuple_param_expects_map_not_number",
      "tests.test_param_error_paths.TestTupleParamExpectingMethod.test_tuple_param_expects_map_not_array",
      "tests.test_signature_edge_cases.test_event_overload_error_by_name",
      "tests.test_signature_edge_cases.test_function_signature_with_whitespace_error",
      "tests.test_abi_edge_cases.test_abi_duplicate_internal_type",
      "tests.test_abi_edge_cases.test_abi_missing_param_type",
      "tests.test_decoder_edge_cases.test_lenient_uint_very_large_ether_value",
      "tests.test_serde_duplicate_fields.TestParamDuplicateFields.test_duplicate_type_field_param",
      "tests.test_serde_duplicate_fields.TestTupleParamDuplicateFields.test_duplicate_name_field_tuple_param",
      "tests.test_serde_duplicate_fields.TestTupleParamDuplicateFields.test_duplicate_type_field_tuple_param",
      "tests.test_serde_duplicate_fields.TestTupleParamDuplicateFields.test_duplicate_components_field_tuple_param",
      "tests.test_signature_edge_cases.test_function_signature_invalid_type_name",
      "tests.test_abi_edge_cases.test_tuple_param_duplicate_internal_type",
      "tests.test_abi_edge_cases.test_event_duplicate_indexed_field",
      "tests.test_abi_edge_cases.test_tuple_param_duplicate_name",
      "eval.tests.test_argparse_validation.test_encode_params_bool_is_case_sensitive",
      "eval.tests.test_argparse_validation.test_option_requires_value_decode_params_t",
      "eval.tests.test_argparse_validation.test_too_many_positionals_for_decode_params_errors",
      "eval.tests.test_argparse_validation.test_unknown_flag_in_subcommand_errors",
      "eval.tests.test_argparse_validation.test_short_option_equal_syntax_supported_decode_params_t_equals",
      "eval.tests.test_function_abi_file.test_encode_function_invalid_name_is_error_to_stderr",
      "eval.tests.test_subcommand_dispatch.test_help_subcommand_accepts_args_but_not_help_flag",
      "tests.test_encode_function.test_encode_function_extra_params_ignored",
      "eval.tests.test_cli_externalized.test_ext_cli_int_encode_overflow_message",
      "eval.tests.test_cli_externalized.test_ext_cli_uint_requires_decimal_input_error_message",
      "eval.tests.test_cli_externalized.test_ext_cli_int_encode_below_min_underflow_message",
      "eval.tests.test_cli_externalized.test_ext_cli_int_encode_above_max_overflow_message"
    ],
    "failed_tests_omitted": 0,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 1053,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "rust-ethereum__ethabi.b1710ad",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "2353280",
    "calls": "55",
    "created_at": "2026-05-17T14:48:47.553470+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "3.1378",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "2489218",
    "instance_id": "rust-ethereum__ethabi.b1710ad",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "925",
    "n_system_errors": "0",
    "n_tests": "997",
    "n_warnings": "0",
    "output_tokens": "42717",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "13854",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-rust-ethereum-ethabi",
    "run_version": "20260517T094700Z",
    "score": "0.9277833500501504",
    "session_ended_at": "2026-05-17T15:01:34.583Z",
    "session_started_at": "2026-05-17T14:48:50.683Z",
    "test_branch_errors": "{}",
    "total_tokens": "2531935",
    "wall_clock_seconds": "763"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./__pycache__",
      "./__pycache__/ethabi_cli.cpython-312.pyc",
      "./compile.sh",
      "./ethabi_cli.py",
      "./executable",
      "./fixtures.abi",
      "./tuple.abi"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-rust-ethereum-ethabi",
  "run_version": "20260517T094700Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
