{ "agent_trace": { "codex_logs_available_local_only": true, "raw_logs_published": false }, "collected_at": "2026-05-18T13:24:59.768045+00:00", "docker_cpus": 16, "docker_memory": "30g", "eval": { "error_code": null, "failed_tests": [ "eval.tests.test_02_compression.test_compress_explicit_flag", "eval.tests.test_07_dictionaries.test_train_dictionary_basic", "eval.tests.test_14_sparse.test_sparse_mode_with_file", "eval.tests.test_17_additional_options.test_no_dictID_option", "eval.tests.test_17_additional_options.test_no_mmap_dict_option", "eval.tests.test_18_error_handling.test_decompress_truncated_data", "eval.tests.test_17_additional_options.test_mmap_dict_option", "eval.tests.test_18_error_handling.test_read_from_directory", "eval.tests.test_18_error_handling.test_invalid_thread_count", "eval.tests.test_18_error_handling.test_decompress_invalid_data", "eval.tests.test_22_patch_mode.test_patch_with_nonexistent_reference", "eval.tests.test_23_trace_logging.test_trace_basic", "eval.tests.test_23_trace_logging.test_trace_decompress", "eval.tests.test_23_trace_logging.test_trace_with_threads", "eval.tests.test_23_trace_logging.test_trace_with_compression_levels", "eval.tests.test_07_dictionaries.test_compress_with_dictionary", "eval.tests.test_07_dictionaries.test_train_with_maxdict", "eval.tests.test_18_error_handling.test_train_dictionary_with_insufficient_data", "eval.tests.test_23_trace_logging.test_trace_append_mode", "eval.tests.test_23_trace_logging.test_trace_file_header", "eval.tests.test_07_dictionaries.test_decompress_with_dictionary", "eval.tests.test_07_dictionaries.test_train_with_dictID", "eval.tests.test_advanced_options.test_memory_limit", "eval.tests.test_basic.test_verbose_flag", "eval.tests.test_coverage_gaps.test_exclude_compressed", "eval.tests.test_error_handling.test_truncated_compressed_file", "eval.tests.test_error_paths.test_compress_read_permission_denied", "eval.tests.test_error_paths.test_compress_symlink", "eval.tests.test_error_paths.test_compress_write_permission_denied", "eval.tests.test_error_paths.test_invalid_long_value", "eval.tests.test_extended_coverage.test_decompress_multiple_files", "eval.tests.test_error_paths_extended.test_stdin_stdout_edge_cases", "eval.tests.test_extended_coverage.test_benchmark_range", "eval.tests.test_error_paths.test_benchmark_on_non_existent_file", "eval.tests.test_error_paths_extended.test_corrupted_file_detection", "eval.tests.test_extended_coverage.test_benchmark_per_file", "eval.tests.test_error_paths.test_invalid_thread_count", "eval.tests.test_extended_coverage.test_train_legacy_parameters", "eval.tests.test_extended_coverage.test_dictionary_id_explicit", "eval.tests.test_final_push.test_dictionary_extensive", "eval.tests.test_missing_features.test_very_verbose_output", "eval.tests.test_special_modes.test_benchmark_with_level", "eval.tests.test_special_modes.test_multiple_verbose", "tests.test_advanced_decompression.test_test_mode_verbose", "tests.test_advanced_compression.test_patch_from_basic_compression", "tests.test_benchfn_gap.test_benchmark_multiple_iterations_timing_consistency", "tests.test_benchzstd_gap.test_benchmark_synthetic_high_compressibility", "tests.test_benchmark.test_benchmark_split_chunks", "tests.test_advanced_compression.test_exclude_compressed_with_gz_format", "tests.test_benchzstd_gap.test_benchmark_quiet_mode_compact_output", "tests.test_advanced_decompression.test_dictionary_decompression_without_dict_fails", "tests.test_benchmark.test_benchmark_progress_indicators", "tests.test_benchfn_gap.test_benchmark_stress_rapid_level_transitions", "tests.test_advanced_decompression.test_sparse_file_with_data_and_holes", "tests.test_advanced_compression.test_stream_size_incorrect_value_error", "tests.test_benchfn_gap.test_benchmark_with_dictionary_and_multiple_levels", "tests.test_datagen_gap.test_benchmark_sparse_content_generation_150_percent", "tests.test_compression_levels.test_fast_mode_size_ordering", "tests.test_dibio_gap.test_train_all_parameters_combined", "tests.test_benchzstd_gap.test_benchmark_very_small_chunk_split", "tests.test_advanced_decompression.test_test_mode_corrupted_file", "tests.test_benchmark.test_benchmark_stdin_uses_lorem_ipsum", "tests.test_benchzstd_gap.test_benchmark_no_files_uses_lorem_ipsum", "tests.test_advanced_compression.test_patch_apply_decompression", "tests.test_benchmark.test_benchmark_partial_missing_files", "tests.test_advanced_decompression.test_dictionary_decompression_with_wrong_dict_fails", "tests.test_benchfn_gap.test_benchmark_stdin_with_levels_and_iterations", "tests.test_benchmark.test_benchmark_basic_default_level", "tests.test_advanced_decompression.test_sparse_large_hole_at_end", "tests.test_advanced_compression.test_patch_from_with_stream_size_enables_stdin", "tests.test_advanced_compression.test_patch_from_with_multiple_files_fails", "tests.test_datagen_gap.test_benchmark_100_percent_compressibility", "tests.test_datagen_gap.test_benchmark_multiple_compression_levels", "tests.test_dibio_gap.test_train_with_large_files_respects_samplesize_limit", "tests.test_benchzstd_gap.test_benchmark_multiple_iterations", "tests.test_advanced_decompression.test_test_mode_truncated_file", "tests.test_benchmark.test_benchmark_level_capped_at_max", "tests.test_benchzstd_gap.test_benchmark_capped_at_max_level", "tests.test_benchmark.test_benchmark_directory_input_error", "tests.test_advanced_compression.test_patch_from_compression_efficiency" ], "failed_tests_omitted": 592, "public_eval_path": "eval.json", "summary_path": "eval-summary.json", "test_branch_errors": {}, "test_records": 2369, "warnings": [] }, "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "instance_id": "facebook__zstd.1168da0", "metrics": { "almost_resolved": "False", "cached_input_tokens": "3720576", "calls": "77", "created_at": "2026-05-17T11:01:27.134996+00:00", "docker_cpus": "16", "docker_memory": "30g", "error_code": "", "estimated_cost_usd": "4.5443", "evaluator_problem": "False", "host_machine": "x86_64", "host_system": "Linux", "inference_mode": "mini-swe-compatible-nointernet", "input_tokens": "3953879", "instance_id": "facebook__zstd.1168da0", "long_context_calls": "0", "model": "gpt-5.5", "n_resolved_tests": "1419", "n_system_errors": "0", "n_tests": "2038", "n_warnings": "0", "output_tokens": "50584", "paper_compliant": "False", "pricing_source": "https://developers.openai.com/api/docs/models/gpt-5.5", "reasoning_effort": "xhigh", "reasoning_output_tokens": "14951", "resolved": "False", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-facebook-zstd", "run_version": "", "score": "0.696270853778214", "session_ended_at": "2026-05-17T11:15:11.274Z", "session_started_at": "2026-05-17T11:01:30.215Z", "test_branch_errors": "{}", "total_tokens": "4004463", "wall_clock_seconds": "821" }, "model": "gpt-5.5", "package": { "contents": [ ".", "./compile.sh", "./executable", "./main.c" ], "contents_omitted": 0, "submission_available_local_only": true }, "paper_compliant": false, "paper_mode": false, "reasoning_effort": "xhigh", "run_name": "cpx62-miniswecompat-xhigh-20260517T094700Z-facebook-zstd", "run_version": "", "usage_audit": { "available_local_artifact": true, "public_path": "usage-audit.json" } }