{
  "schema": "diskcover-public-test-reports-v1",
  "n": 12,
  "report_scope": "Retrospective single-run records with answers withheld; the publisher clarified that the file ban covers only local materials existing before the test.",
  "records_comparable": false,
  "records": [
    {
      "record_id": "n12-deepseek-v4-pro-max-20261002",
      "test_id": "T_20261003T005110Z_db9dfa6a",
      "n": 12,
      "model": "deepseek-v4-pro/max",
      "model_id": "deepseek-v4-pro",
      "reasoning_effort": "max",
      "provider_recorded": "deepseek-official",
      "test_date_utc": "2026-10-03",
      "test_date_local": "2026-10-02",
      "local_timezone": "America/New_York",
      "status": "failed_incorrect_optimal_radius",
      "score": "0",
      "score_scope": "benchmark_failure_score",
      "acceptance_status": "failed_incorrect_optimal_radius_exact_better_cover",
      "runs": 1,
      "elapsed_seconds": "8015.612",
      "main_system_accumulated_seconds": null,
      "goal_cumulative_seconds": null,
      "timing_scope": "first_goal_create_to_final_substantive_assistant_message_includes_recovery_and_blocked_waiting",
      "test_start_utc": "2026-10-03T00:51:10.682000+00:00",
      "final_submission_utc": "2026-10-03T03:04:46.294000+00:00",
      "deadline_utc": "2026-10-03T12:51:10.682000+00:00",
      "original_budget_seconds": "43200",
      "submission_within_budget": true,
      "valid_completion_within_budget": false,
      "source_event_seqs": {
        "start": 10,
        "goal_blocked": 1140,
        "goal_mark_complete": 1188,
        "final_submission": 1193,
        "final_turn_end": 1196
      },
      "turn_interval_sum_seconds": "4849.269",
      "turn_interval_sum_is_system_accumulated_time": false,
      "token_usage": {
        "inputTokens": 163009,
        "outputTokens": 382409,
        "cacheReadTokens": 36592640,
        "cacheWriteTokens": 0,
        "totalTokens": 37138058,
        "usage_record_count": 161,
        "goal_tokens": null,
        "currency_cost": null,
        "scope": "saved_assistant_message_usage; not complete invoiced usage"
      },
      "hardware": {
        "cpu": "AMD Ryzen 9 8945HX with Radeon Graphics",
        "memory_generation": "DDR5",
        "memory_gib": 32,
        "snapshot_scope": "queried_during_report_preparation_not_at_task_start"
      },
      "environment": {
        "python": "3.12.3",
        "sympy": "1.14.0",
        "mpmath": "1.3.0",
        "numpy": "2.5.3",
        "gcc": "13.3.0",
        "scipy": "1.18.1",
        "scipy_version_source": "original_submission_declaration_not_separate_start_snapshot",
        "versions_source": "actual_test_tool_output_except_scipy",
        "package_preinstallation_status": "not_fully_known"
      },
      "verification": {
        "outcome": "exact_strictly_better_continuous_cover_refutes_submitted_optimum",
        "distinct_critical_candidates": 293,
        "exact_distance_comparisons": 2071,
        "result": "ACCEPT",
        "isolated_packaged_replay_passed": true,
        "true_global_optimum_certified": false,
        "original_candidate_cover_failure_asserted": false,
        "original_optimization_pipeline_fully_replayed": false
      },
      "archive_scope": {
        "records": 1198,
        "header_plus_contiguous_seq": "header + seq 0..1196",
        "original_truncated_tool_results": 18,
        "completeness": "complete_available_local_snapshot; not provider_internal_full_records"
      },
      "resource_compliance_audit": "not_complete; mathematical_failure_decisive",
      "prompt_artifacts": [
        {
          "kind": "main",
          "original_text_url": "reports/n12-deepseek-main-prompt.original.txt",
          "sha256": "b4489ab90a3fc8ac5e42457ed5c1f804c7683a85df7cdd4cbf5ae9863516ba1d",
          "preserve_original_bytes": true
        }
      ],
      "report_urls": {
        "zh": "record-n12-deepseek-v4-pro-max-20261002.zh.html",
        "en": "record-n12-deepseek-v4-pro-max-20261002.html"
      },
      "answer_disclosure": "no_radii_coefficients_centers_or_private_conversations",
      "limitations": [
        "One run; no frozen formal comparison contract.",
        "Exact counterexample refutes this submission; it does not identify the true global optimum.",
        "Full source conversations and mathematical evidence remain private locally.",
        "System cumulative time, separate Goal usage and invoiced cost are unavailable."
      ]
    }
  ]
}