{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false
  },
  "collected_at": "2026-05-18T13:25:02.878059+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "eval.tests.test_advanced_features.test_blockquote_nested",
      "eval.tests.test_advanced_features.test_preformatted_text",
      "eval.tests.test_advanced_features.test_url_with_query_params",
      "eval.tests.test_advanced_features.test_nested_lists",
      "eval.tests.test_advanced_features.test_cite_tag",
      "eval.tests.test_advanced_features.test_relative_url_with_dots",
      "eval.tests.test_advanced_features.test_multiple_classes",
      "eval.tests.test_advanced_features.test_pseudo_class_selector",
      "eval.tests.test_advanced_features.test_emphasis_within_strong",
      "eval.tests.test_advanced_features.test_mark_tag",
      "eval.tests.test_advanced_features.test_address_tag",
      "eval.tests.test_advanced_features.test_sub_tag",
      "eval.tests.test_advanced_features.test_figure_and_figcaption",
      "eval.tests.test_advanced_features.test_mailto_link",
      "eval.tests.test_advanced_features.test_image_without_alt",
      "eval.tests.test_advanced_features.test_empty_elements",
      "eval.tests.test_advanced_features.test_multiple_strong_in_paragraph",
      "eval.tests.test_advanced_features.test_link_within_strong",
      "eval.tests.test_advanced_features.test_time_tag",
      "eval.tests.test_advanced_features.test_attribute_selector",
      "eval.tests.test_advanced_features.test_abbr_tag",
      "eval.tests.test_advanced_features.test_link_with_title",
      "eval.tests.test_advanced_features.test_data_url",
      "eval.tests.test_advanced_features.test_details_and_summary",
      "eval.tests.test_advanced_features.test_sup_tag",
      "eval.tests.test_advanced_features.test_kbd_tag",
      "eval.tests.test_advanced_features.test_whitespace_preservation_in_code",
      "eval.tests.test_advanced_features.test_url_with_fragment",
      "eval.tests.test_advanced_features.test_mixed_list_types",
      "eval.tests.test_advanced_features.test_definition_list",
      "eval.tests.test_advanced_features.test_code_with_language",
      "eval.tests.test_advanced_features.test_tel_link",
      "eval.tests.test_core_conversion.test_convert_multiple_paragraphs",
      "eval.tests.test_domain.test_domain_relative_image",
      "eval.tests.test_basic_invocation.test_help_flag",
      "eval.tests.test_core_conversion.test_convert_em",
      "eval.tests.test_domain.test_no_domain_relative_link",
      "eval.tests.test_advanced_features.test_list_with_paragraphs",
      "eval.tests.test_domain.test_domain_with_http",
      "eval.tests.test_core_conversion.test_convert_code_inline",
      "eval.tests.test_error_handling.test_nested_unclosed_tags",
      "eval.tests.test_core_conversion.test_convert_hr_tag",
      "eval.tests.test_basic_invocation.test_stdin_whitespace_only",
      "eval.tests.test_core_conversion.test_convert_h3",
      "eval.tests.test_error_handling.test_malformed_html",
      "eval.tests.test_core_conversion.test_convert_unordered_list",
      "eval.tests.test_error_handling.test_deeply_nested_tags",
      "eval.tests.test_error_handling.test_style_tag",
      "eval.tests.test_core_conversion.test_convert_complex_document",
      "eval.tests.test_domain.test_domain_absolute_link_unchanged",
      "eval.tests.test_core_conversion.test_convert_h1",
      "eval.tests.test_domain.test_domain_with_path",
      "eval.tests.test_domain.test_domain_without_protocol",
      "eval.tests.test_basic_invocation.test_stdin_basic_conversion",
      "eval.tests.test_core_conversion.test_convert_strong_default",
      "eval.tests.test_core_conversion.test_convert_link",
      "eval.tests.test_core_conversion.test_convert_pre_code_block",
      "eval.tests.test_basic_invocation.test_version_flag",
      "eval.tests.test_domain.test_domain_relative_link",
      "eval.tests.test_error_handling.test_special_html_entities",
      "eval.tests.test_core_conversion.test_convert_ordered_list",
      "eval.tests.test_error_handling.test_unicode_characters",
      "eval.tests.test_error_handling.test_script_tag",
      "eval.tests.test_error_handling.test_comment_handling",
      "eval.tests.test_error_handling.test_null_bytes",
      "eval.tests.test_core_conversion.test_convert_br_tag",
      "eval.tests.test_basic_invocation.test_stdin_empty_input",
      "eval.tests.test_escaping.test_escape_brackets",
      "eval.tests.test_core_conversion.test_convert_blockquote",
      "eval.tests.test_escaping.test_escape_asterisk",
      "eval.tests.test_core_conversion.test_convert_nested_tags",
      "eval.tests.test_core_conversion.test_convert_strong_underscore",
      "eval.tests.test_core_conversion.test_convert_image",
      "eval.tests.test_basic_invocation.test_version_short_flag",
      "eval.tests.test_escaping.test_real_vs_fake_bold",
      "eval.tests.test_core_conversion.test_convert_h2",
      "eval.tests.test_error_handling.test_very_long_line",
      "eval.tests.test_escaping.test_escape_list_markers",
      "eval.tests.test_escaping.test_ampersand_escape",
      "eval.tests.test_escaping.test_quotes_handling"
    ],
    "failed_tests_omitted": 846,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 974,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "mini-swe-compatible-nointernet",
  "instance_id": "johanneskaufmann__html-to-markdown.3006818",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "4546816",
    "calls": "90",
    "created_at": "2026-05-17T11:52:25.095885+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "4.5421",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "mini-swe-compatible-nointernet",
    "input_tokens": "4712346",
    "instance_id": "johanneskaufmann__html-to-markdown.3006818",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "34",
    "n_system_errors": "0",
    "n_tests": "885",
    "n_warnings": "0",
    "output_tokens": "48035",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "14236",
    "resolved": "False",
    "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-johanneskaufmann-html-to-markdown",
    "run_version": "",
    "score": "0.0384180790960452",
    "session_ended_at": "2026-05-17T12:06:24.763Z",
    "session_started_at": "2026-05-17T11:52:28.125Z",
    "test_branch_errors": "{}",
    "total_tokens": "4760381",
    "wall_clock_seconds": "836"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./compile.sh",
      "./executable",
      "./html2markdown.py"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": false,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-johanneskaufmann-html-to-markdown",
  "run_version": "",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
