{
  "agent_trace": {
    "codex_logs_available_local_only": true,
    "raw_logs_published": false,
    "summary_path": "agent-summary.json"
  },
  "codex_version": "codex-cli 0.131.0",
  "collected_at": "2026-05-19T20:17:59.541080+00:00",
  "docker_cpus": 16,
  "docker_memory": "30g",
  "eval": {
    "error_code": null,
    "failed_tests": [
      "tests.test_basic.test_stdin_large_input",
      "tests.test_edge_cases_final.test_keyed_mode_with_escaped_filename",
      "tests.test_check.test_check_windows_path_on_linux",
      "tests.test_check.test_check_unicode_replacement_rejected",
      "tests.test_basic.test_no_args_reads_stdin",
      "tests.test_advanced.test_seek_and_length_with_stdin",
      "tests.test_errors.test_raw_with_check_conflict",
      "tests.test_check.test_check_conflicts_with_length",
      "tests.test_errors.test_multiple_stdin_indicators",
      "tests.test_check.test_check_stdin_checkfile",
      "tests.test_advanced.test_length_with_keyed_mode",
      "tests.test_check.test_check_malformed_lines_reported",
      "tests.test_basic.test_stdin_small_string",
      "tests.test_errors.test_seek_and_length_combined",
      "tests.test_errors.test_raw_with_tag_outputs_raw",
      "tests.test_final_gaps.test_keyed_mode_65_bytes",
      "tests.test_errors.test_keyed_mode_cannot_use_stdin_dash",
      "tests.test_advanced.test_no_mmap_with_stdin",
      "tests.test_check.test_check_invalid_escape_sequence",
      "tests.test_check.test_check_conflicts_with_no_names",
      "tests.test_edge_cases_final.test_carriage_return_at_different_positions",
      "tests.test_check.test_check_invalid_hex_characters",
      "tests.test_errors.test_dev_zero_hash",
      "tests.test_edge_cases_final.test_multiple_escape_sequences_in_filename",
      "tests.test_advanced.test_seek_with_keyed_mode",
      "tests.test_basic.test_explicit_dash_for_stdin",
      "tests.test_basic.test_stdin_binary_data",
      "tests.test_check.test_check_blank_lines_reported",
      "tests.test_errors.test_derive_key_basic",
      "tests.test_errors.test_length_one_byte",
      "tests.test_guts_coverage.test_incremental_update_logic",
      "tests.test_io.test_stdin_small_input",
      "tests.test_errors.test_keyed_mode_key_too_short",
      "tests.test_check.test_check_trailing_backslash_rejected",
      "tests.test_edge_cases_final.test_all_three_escape_types_mixed",
      "tests.test_edge_cases_final.test_incomplete_escape_sequence_rejected",
      "tests.test_check.test_check_conflicts_with_raw",
      "tests.test_errors.test_large_seek_offset",
      "tests.test_check.test_check_empty_filename_rejected",
      "tests.test_advanced.test_no_mmap_with_keyed_mode",
      "tests.test_basic.test_mixed_files_and_stdin",
      "tests.test_basic.test_stdin_unicode",
      "tests.test_final_gaps.test_keyed_mode_1025_bytes",
      "tests.test_errors.test_derive_key_empty_context",
      "tests.test_keyed.test_keyed_test_vector_input_len_0",
      "tests.test_errors.test_length_one_hundred",
      "tests.test_harvest.test_hash_one",
      "tests.test_io.test_stdin_large_input",
      "tests.test_errors.test_keyed_mode_key_too_long",
      "tests.test_edge_cases_final.test_long_filename_with_multiple_escapes",
      "tests.test_errors.test_check_with_keyed_conflict",
      "tests.test_check.test_check_conflicts_with_tag",
      "tests.test_check.test_check_null_character_rejected",
      "tests.test_lib.test_extended_output_64_bytes",
      "tests.test_lib.test_derive_key_mode",
      "tests.test_advanced.test_length_with_stdin",
      "tests.test_harvest.test_newline_and_backslash_escaping_on_unix",
      "tests.test_escape_sequences.test_carriage_return_escape",
      "tests.test_final_gaps.test_stdin_65_bytes",
      "tests.test_keyed.test_keyed_test_vector_input_len_1",
      "tests.test_guts_coverage.test_chunk_state_via_normal_hash",
      "tests.test_errors.test_no_names_flag",
      "tests.test_harvest.test_hash_one_tag",
      "tests.test_io.test_permission_denied_error",
      "tests.test_io.test_file_just_under_16kb",
      "tests.test_errors.test_filename_with_carriage_return_escaped",
      "tests.test_harvest.test_check",
      "tests.test_errors.test_check_with_derive_key_conflict",
      "tests.test_keyed.test_keyed_test_vector_input_len_128",
      "tests.test_lib.test_seek_offset_middle",
      "tests.test_keyed.test_keyed_differs_from_unkeyed",
      "tests.test_advanced.test_seek_with_stdin",
      "tests.test_harvest.test_slash_normalization_on_windows",
      "tests.test_harvest.test_invalid_unicode_on_unix",
      "tests.test_final_gaps.test_stdin_1025_bytes",
      "tests.test_lib.test_seek_and_length_one_byte",
      "tests.test_guts_coverage.test_multi_chunk_hash_exercises_parent_cv",
      "tests.test_errors.test_tag_format_output",
      "tests.test_lib.test_seek_max_u64",
      "tests.test_keyed.test_keyed_multiple_files_different_keys"
    ],
    "failed_tests_omitted": 152,
    "public_eval_path": "eval.json",
    "summary_path": "eval-summary.json",
    "test_branch_errors": {},
    "test_records": 687,
    "warnings": []
  },
  "host_machine": "x86_64",
  "host_system": "Linux",
  "inference_mode": "paper-prompt-nointernet",
  "instance_id": "blake3-team__blake3.15e83a5",
  "metrics": {
    "almost_resolved": "False",
    "cached_input_tokens": "2544384",
    "calls": "58",
    "codex_version": "codex-cli 0.131.0",
    "created_at": "2026-05-19T00:02:34.256032+00:00",
    "docker_cpus": "16",
    "docker_memory": "30g",
    "error_code": "",
    "estimated_cost_usd": "3.4266",
    "evaluator_problem": "False",
    "host_machine": "x86_64",
    "host_system": "Linux",
    "inference_mode": "paper-prompt-nointernet",
    "input_tokens": "2709054",
    "instance_id": "blake3-team__blake3.15e83a5",
    "long_context_calls": "0",
    "model": "gpt-5.5",
    "n_resolved_tests": "423",
    "n_system_errors": "0",
    "n_tests": "647",
    "n_warnings": "0",
    "output_tokens": "44370",
    "paper_compliant": "False",
    "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5",
    "reasoning_effort": "xhigh",
    "reasoning_output_tokens": "8592",
    "resolved": "False",
    "run_name": "cpx62-paperprompt-xhigh-shard-0-of-5-20260518T232006Z-blake3-team-blake3",
    "run_version": "20260518T232006Z",
    "score": "0.6537867078825348",
    "session_ended_at": "2026-05-19T00:13:24.376Z",
    "session_started_at": "2026-05-19T00:02:42.168Z",
    "test_branch_errors": "{}",
    "total_tokens": "2753424",
    "wall_clock_seconds": "642"
  },
  "model": "gpt-5.5",
  "package": {
    "contents": [
      ".",
      "./.git",
      "./.git/COMMIT_EDITMSG",
      "./.git/HEAD",
      "./.git/branches",
      "./.git/config",
      "./.git/description",
      "./.git/hooks",
      "./.git/hooks/applypatch-msg.sample",
      "./.git/hooks/commit-msg.sample",
      "./.git/hooks/fsmonitor-watchman.sample",
      "./.git/hooks/post-update.sample",
      "./.git/hooks/pre-applypatch.sample",
      "./.git/hooks/pre-commit.sample",
      "./.git/hooks/pre-merge-commit.sample",
      "./.git/hooks/pre-push.sample",
      "./.git/hooks/pre-rebase.sample",
      "./.git/hooks/pre-receive.sample",
      "./.git/hooks/prepare-commit-msg.sample",
      "./.git/hooks/push-to-checkout.sample",
      "./.git/hooks/update.sample",
      "./.git/index",
      "./.git/info",
      "./.git/info/exclude",
      "./.git/logs",
      "./.git/logs/HEAD",
      "./.git/logs/refs",
      "./.git/logs/refs/heads",
      "./.git/logs/refs/heads/master",
      "./.git/objects",
      "./.git/objects/0e",
      "./.git/objects/0e/259d42c996742e9e3cba14c677129b2c1b6311",
      "./.git/objects/2d",
      "./.git/objects/2d/50c2d3b586e702d6d399c82ec24502525b26de",
      "./.git/objects/35",
      "./.git/objects/35/00819977bf1cea48855e7712efb2863d8866ed",
      "./.git/objects/35/c4e7f8251806df30e8ca1ba63a6d9fb4b5c691",
      "./.git/objects/7b",
      "./.git/objects/7b/d65ca3cd14ea6b771e168a33cb5a41feedfa23",
      "./.git/objects/7c",
      "./.git/objects/7c/c2fd5cd45ff2f0e582eab19fcfd38d77bfd8a2",
      "./.git/objects/80",
      "./.git/objects/80/18dccabefb9fbf6c3aaf101536d887082bb4fc",
      "./.git/objects/85",
      "./.git/objects/85/6562a793791a0e5ce5fb60a8f12b696353a758",
      "./.git/objects/8d",
      "./.git/objects/8d/11bec0e86f88276b155cd3214a3de45cdafeb7",
      "./.git/objects/a5",
      "./.git/objects/a5/0da0ce93bdbed3123c546756e619275b151a71",
      "./.git/objects/c7",
      "./.git/objects/c7/b0be82d013d63a96a223ca19357310bb95050d",
      "./.git/objects/c9",
      "./.git/objects/c9/f3d16a6d617400b114a955fbbd1945ff7369e3",
      "./.git/objects/d0",
      "./.git/objects/d0/d0767a68d9cc36a2f27c390a07b974216e8ddc",
      "./.git/objects/d5",
      "./.git/objects/d5/12ca94d0ca6bf6a7272b16c83f51b7045902ca",
      "./.git/objects/f9",
      "./.git/objects/f9/405c4612521746d0e141e9a10751dc318d40d5",
      "./.git/objects/info",
      "./.git/objects/pack",
      "./.git/refs",
      "./.git/refs/heads",
      "./.git/refs/heads/master",
      "./.git/refs/tags",
      "./LICENSE_A2",
      "./LICENSE_A2LLVM",
      "./LICENSE_CC0",
      "./README.md",
      "./b3sum",
      "./b3sum/LICENSE_A2",
      "./b3sum/LICENSE_A2LLVM",
      "./b3sum/LICENSE_CC0",
      "./b3sum/README.md",
      "./compile.sh",
      "./executable",
      "./main.c",
      "./media",
      "./media/B3.svg",
      "./media/BLAKE3.svg",
      "./media/speed.svg"
    ],
    "contents_omitted": 0,
    "submission_available_local_only": true
  },
  "paper_compliant": false,
  "paper_mode": true,
  "reasoning_effort": "xhigh",
  "run_name": "cpx62-paperprompt-xhigh-shard-0-of-5-20260518T232006Z-blake3-team-blake3",
  "run_version": "20260518T232006Z",
  "usage_audit": {
    "available_local_artifact": true,
    "public_path": "usage-audit.json"
  }
}
