{
  "schema_version": 1,
  "date_utc": "2026-10-06",
  "scope": "Owner-run original synthetic development diagnostics on eight exposed task pairs, two seeds and three conditions. Not CooperBench, a fresh holdout, outside reproduction or a general coordination-performance result.",
  "limits": {
    "aggregate_model_token_cap_per_pair": 25000,
    "artifact_wall_seconds_per_pair": 1800,
    "grading_wall": "separate from artifact wall",
    "local_hardware_electricity_usd": "unmeasured"
  },
  "model": {
    "tag": "qwen3-coder:30b",
    "digest": "06c1097efce0431c2045fe7b2e5108366e43bee1b4603a7aded8f21689e90bca"
  },
  "versions": {
    "v1": {
      "conditions": {
        "single": {
          "attempts": 16,
          "accepted_pairs": 0,
          "feature_a_accepted": 1,
          "feature_b_accepted": 0,
          "statuses": {
            "failed-ValueError": 9,
            "artifact-complete": 1,
            "failed-RuntimeError": 3,
            "failed-JSONDecodeError": 3
          },
          "merge_failures": 0,
          "known_usage_attempts": 16,
          "unknown_usage_attempts": 0,
          "unknown_usage_attempt_ids": [],
          "external_usd": 0,
          "external_usd_per_accepted_pair": null,
          "local_hardware_electricity_usd": "unmeasured",
          "total_economic_cost_per_accepted_pair": null,
          "prompt_tokens_reported_sum": 63056,
          "prompt_tokens_missing_attempts": 0,
          "output_tokens_reported_sum": 18149,
          "output_tokens_missing_attempts": 0,
          "aggregate_tokens_reported_sum": 81205,
          "aggregate_tokens_missing_attempts": 0,
          "model_calls_reported_sum": 55,
          "model_calls_missing_attempts": 0,
          "tool_commands_reported_sum": 91,
          "tool_commands_missing_attempts": 0,
          "messages_reported_sum": 0,
          "messages_missing_attempts": 0,
          "operator_interventions_reported_sum": 0,
          "operator_interventions_missing_attempts": 0,
          "model_merge_fixes_reported_sum": 0,
          "model_merge_fixes_missing_attempts": 0,
          "elapsed_wall_seconds_reported_sum": 306.857,
          "elapsed_wall_seconds_missing_attempts": 0,
          "pending_unknown_requests_from_events": 0,
          "unknown_attempts_without_request_event_metadata": 0,
          "model_tokens_complete": true,
          "fault_injected": 0,
          "fault_not_reached": 0,
          "fault_coverage_unknown_attempts": 0
        },
        "plain": {
          "attempts": 16,
          "accepted_pairs": 0,
          "feature_a_accepted": 0,
          "feature_b_accepted": 0,
          "statuses": {
            "failed-ValueError": 13,
            "failed-RuntimeError": 3
          },
          "merge_failures": 0,
          "known_usage_attempts": 16,
          "unknown_usage_attempts": 0,
          "unknown_usage_attempt_ids": [],
          "external_usd": 0,
          "external_usd_per_accepted_pair": null,
          "local_hardware_electricity_usd": "unmeasured",
          "total_economic_cost_per_accepted_pair": null,
          "prompt_tokens_reported_sum": 59790,
          "prompt_tokens_missing_attempts": 0,
          "output_tokens_reported_sum": 11107,
          "output_tokens_missing_attempts": 0,
          "aggregate_tokens_reported_sum": 70897,
          "aggregate_tokens_missing_attempts": 0,
          "model_calls_reported_sum": 63,
          "model_calls_missing_attempts": 0,
          "tool_commands_reported_sum": 74,
          "tool_commands_missing_attempts": 0,
          "messages_reported_sum": 0,
          "messages_missing_attempts": 0,
          "operator_interventions_reported_sum": 0,
          "operator_interventions_missing_attempts": 0,
          "model_merge_fixes_reported_sum": 0,
          "model_merge_fixes_missing_attempts": 0,
          "elapsed_wall_seconds_reported_sum": 183.637,
          "elapsed_wall_seconds_missing_attempts": 0,
          "pending_unknown_requests_from_events": 0,
          "unknown_attempts_without_request_event_metadata": 0,
          "model_tokens_complete": true,
          "fault_injected": 0,
          "fault_not_reached": 0,
          "fault_coverage_unknown_attempts": 0
        },
        "echo": {
          "attempts": 16,
          "accepted_pairs": 0,
          "feature_a_accepted": 0,
          "feature_b_accepted": 0,
          "statuses": {
            "failed-ValueError": 16
          },
          "merge_failures": 0,
          "known_usage_attempts": 16,
          "unknown_usage_attempts": 0,
          "unknown_usage_attempt_ids": [],
          "external_usd": 0,
          "external_usd_per_accepted_pair": null,
          "local_hardware_electricity_usd": "unmeasured",
          "total_economic_cost_per_accepted_pair": null,
          "prompt_tokens_reported_sum": 3270,
          "prompt_tokens_missing_attempts": 0,
          "output_tokens_reported_sum": 3719,
          "output_tokens_missing_attempts": 0,
          "aggregate_tokens_reported_sum": 6989,
          "aggregate_tokens_missing_attempts": 0,
          "model_calls_reported_sum": 20,
          "model_calls_missing_attempts": 0,
          "tool_commands_reported_sum": 17,
          "tool_commands_missing_attempts": 0,
          "messages_reported_sum": 0,
          "messages_missing_attempts": 0,
          "operator_interventions_reported_sum": 0,
          "operator_interventions_missing_attempts": 0,
          "model_merge_fixes_reported_sum": 0,
          "model_merge_fixes_missing_attempts": 0,
          "elapsed_wall_seconds_reported_sum": 69.786,
          "elapsed_wall_seconds_missing_attempts": 0,
          "pending_unknown_requests_from_events": 0,
          "unknown_attempts_without_request_event_metadata": 0,
          "model_tokens_complete": true,
          "fault_injected": 0,
          "fault_not_reached": 0,
          "fault_coverage_unknown_attempts": 0
        }
      },
      "all_attempts": {
        "attempts": 48,
        "accepted_pairs": 0,
        "feature_a_accepted": 1,
        "feature_b_accepted": 0,
        "statuses": {
          "failed-ValueError": 38,
          "artifact-complete": 1,
          "failed-RuntimeError": 6,
          "failed-JSONDecodeError": 3
        },
        "merge_failures": 0,
        "known_usage_attempts": 48,
        "unknown_usage_attempts": 0,
        "unknown_usage_attempt_ids": [],
        "external_usd": 0,
        "external_usd_per_accepted_pair": null,
        "local_hardware_electricity_usd": "unmeasured",
        "total_economic_cost_per_accepted_pair": null,
        "prompt_tokens_reported_sum": 126116,
        "prompt_tokens_missing_attempts": 0,
        "output_tokens_reported_sum": 32975,
        "output_tokens_missing_attempts": 0,
        "aggregate_tokens_reported_sum": 159091,
        "aggregate_tokens_missing_attempts": 0,
        "model_calls_reported_sum": 138,
        "model_calls_missing_attempts": 0,
        "tool_commands_reported_sum": 182,
        "tool_commands_missing_attempts": 0,
        "messages_reported_sum": 0,
        "messages_missing_attempts": 0,
        "operator_interventions_reported_sum": 0,
        "operator_interventions_missing_attempts": 0,
        "model_merge_fixes_reported_sum": 0,
        "model_merge_fixes_missing_attempts": 0,
        "elapsed_wall_seconds_reported_sum": 560.28,
        "elapsed_wall_seconds_missing_attempts": 0,
        "pending_unknown_requests_from_events": 0,
        "unknown_attempts_without_request_event_metadata": 0,
        "model_tokens_complete": true,
        "fault_injected": 0,
        "fault_not_reached": 0,
        "fault_coverage_unknown_attempts": 0
      },
      "echo_vs_plain": {
        "task_cluster_count": 8,
        "seeds_per_task": 2,
        "paired_task_means": {
          "parcel": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "tariff": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "timeslot": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "citation": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "telemetry": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "routing": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "version": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "allocation": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          }
        },
        "mean_task_difference": 0,
        "descriptive_task_cluster_bootstrap_percentile_95": [
          0.0,
          0.0
        ],
        "bootstrap_seed": 20261006,
        "bootstrap_replicates": 10000,
        "interpretation": "descriptive only; eight original development tasks do not establish quality superiority, equivalence or generalization"
      },
      "fault_arm": null,
      "analysis_sha256": "dd8de3ca45f291b30b7acf6c4a34973dc0d062ca69e935175171269c43bf987d"
    },
    "v2": {
      "conditions": {
        "single": {
          "attempts": 16,
          "accepted_pairs": 8,
          "feature_a_accepted": 11,
          "feature_b_accepted": 10,
          "statuses": {
            "artifact-complete": 14,
            "failed-ValueError": 2
          },
          "merge_failures": 0,
          "known_usage_attempts": 16,
          "unknown_usage_attempts": 0,
          "unknown_usage_attempt_ids": [],
          "external_usd": 0,
          "external_usd_per_accepted_pair": 0,
          "local_hardware_electricity_usd": "unmeasured",
          "total_economic_cost_per_accepted_pair": null,
          "prompt_tokens_reported_sum": 26024,
          "prompt_tokens_missing_attempts": 0,
          "output_tokens_reported_sum": 3241,
          "output_tokens_missing_attempts": 0,
          "aggregate_tokens_reported_sum": 29265,
          "aggregate_tokens_missing_attempts": 0,
          "model_calls_reported_sum": 28,
          "model_calls_missing_attempts": 0,
          "tool_commands_reported_sum": 45,
          "tool_commands_missing_attempts": 0,
          "messages_reported_sum": 0,
          "messages_missing_attempts": 0,
          "operator_interventions_reported_sum": 0,
          "operator_interventions_missing_attempts": 0,
          "model_merge_fixes_reported_sum": 0,
          "model_merge_fixes_missing_attempts": 0,
          "elapsed_wall_seconds_reported_sum": 63.485,
          "elapsed_wall_seconds_missing_attempts": 0,
          "pending_unknown_requests_from_events": 0,
          "unknown_attempts_without_request_event_metadata": 0,
          "model_tokens_complete": true,
          "fault_injected": 0,
          "fault_not_reached": 0,
          "fault_coverage_unknown_attempts": 0
        },
        "plain": {
          "attempts": 16,
          "accepted_pairs": 0,
          "feature_a_accepted": 2,
          "feature_b_accepted": 1,
          "statuses": {
            "artifact-complete": 3,
            "failed-RuntimeError": 9,
            "merge-conflict": 4
          },
          "merge_failures": 4,
          "known_usage_attempts": 16,
          "unknown_usage_attempts": 0,
          "unknown_usage_attempt_ids": [],
          "external_usd": 0,
          "external_usd_per_accepted_pair": null,
          "local_hardware_electricity_usd": "unmeasured",
          "total_economic_cost_per_accepted_pair": null,
          "prompt_tokens_reported_sum": 214853,
          "prompt_tokens_missing_attempts": 0,
          "output_tokens_reported_sum": 9952,
          "output_tokens_missing_attempts": 0,
          "aggregate_tokens_reported_sum": 224805,
          "aggregate_tokens_missing_attempts": 0,
          "model_calls_reported_sum": 191,
          "model_calls_missing_attempts": 0,
          "tool_commands_reported_sum": 271,
          "tool_commands_missing_attempts": 0,
          "messages_reported_sum": 43,
          "messages_missing_attempts": 0,
          "operator_interventions_reported_sum": 0,
          "operator_interventions_missing_attempts": 0,
          "model_merge_fixes_reported_sum": 0,
          "model_merge_fixes_missing_attempts": 0,
          "elapsed_wall_seconds_reported_sum": 198.153,
          "elapsed_wall_seconds_missing_attempts": 0,
          "pending_unknown_requests_from_events": 0,
          "unknown_attempts_without_request_event_metadata": 0,
          "model_tokens_complete": true,
          "fault_injected": 0,
          "fault_not_reached": 0,
          "fault_coverage_unknown_attempts": 0
        },
        "echo": {
          "attempts": 16,
          "accepted_pairs": 0,
          "feature_a_accepted": 1,
          "feature_b_accepted": 2,
          "statuses": {
            "merge-conflict": 9,
            "artifact-complete": 3,
            "failed-RuntimeError": 4
          },
          "merge_failures": 9,
          "known_usage_attempts": 16,
          "unknown_usage_attempts": 0,
          "unknown_usage_attempt_ids": [],
          "external_usd": 0,
          "external_usd_per_accepted_pair": null,
          "local_hardware_electricity_usd": "unmeasured",
          "total_economic_cost_per_accepted_pair": null,
          "prompt_tokens_reported_sum": 168307,
          "prompt_tokens_missing_attempts": 0,
          "output_tokens_reported_sum": 10194,
          "output_tokens_missing_attempts": 0,
          "aggregate_tokens_reported_sum": 178501,
          "aggregate_tokens_missing_attempts": 0,
          "model_calls_reported_sum": 166,
          "model_calls_missing_attempts": 0,
          "tool_commands_reported_sum": 273,
          "tool_commands_missing_attempts": 0,
          "messages_reported_sum": 52,
          "messages_missing_attempts": 0,
          "operator_interventions_reported_sum": 0,
          "operator_interventions_missing_attempts": 0,
          "model_merge_fixes_reported_sum": 0,
          "model_merge_fixes_missing_attempts": 0,
          "elapsed_wall_seconds_reported_sum": 212.954,
          "elapsed_wall_seconds_missing_attempts": 0,
          "pending_unknown_requests_from_events": 0,
          "unknown_attempts_without_request_event_metadata": 0,
          "model_tokens_complete": true,
          "fault_injected": 0,
          "fault_not_reached": 0,
          "fault_coverage_unknown_attempts": 0
        }
      },
      "all_attempts": {
        "attempts": 48,
        "accepted_pairs": 8,
        "feature_a_accepted": 14,
        "feature_b_accepted": 13,
        "statuses": {
          "artifact-complete": 20,
          "merge-conflict": 13,
          "failed-RuntimeError": 13,
          "failed-ValueError": 2
        },
        "merge_failures": 13,
        "known_usage_attempts": 48,
        "unknown_usage_attempts": 0,
        "unknown_usage_attempt_ids": [],
        "external_usd": 0,
        "external_usd_per_accepted_pair": 0,
        "local_hardware_electricity_usd": "unmeasured",
        "total_economic_cost_per_accepted_pair": null,
        "prompt_tokens_reported_sum": 409184,
        "prompt_tokens_missing_attempts": 0,
        "output_tokens_reported_sum": 23387,
        "output_tokens_missing_attempts": 0,
        "aggregate_tokens_reported_sum": 432571,
        "aggregate_tokens_missing_attempts": 0,
        "model_calls_reported_sum": 385,
        "model_calls_missing_attempts": 0,
        "tool_commands_reported_sum": 589,
        "tool_commands_missing_attempts": 0,
        "messages_reported_sum": 95,
        "messages_missing_attempts": 0,
        "operator_interventions_reported_sum": 0,
        "operator_interventions_missing_attempts": 0,
        "model_merge_fixes_reported_sum": 0,
        "model_merge_fixes_missing_attempts": 0,
        "elapsed_wall_seconds_reported_sum": 474.592,
        "elapsed_wall_seconds_missing_attempts": 0,
        "pending_unknown_requests_from_events": 0,
        "unknown_attempts_without_request_event_metadata": 0,
        "model_tokens_complete": true,
        "fault_injected": 0,
        "fault_not_reached": 0,
        "fault_coverage_unknown_attempts": 0
      },
      "echo_vs_plain": {
        "task_cluster_count": 8,
        "seeds_per_task": 2,
        "paired_task_means": {
          "parcel": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "tariff": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "timeslot": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "citation": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "telemetry": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "routing": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "version": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          },
          "allocation": {
            "echo": 0,
            "plain": 0,
            "difference": 0
          }
        },
        "mean_task_difference": 0,
        "descriptive_task_cluster_bootstrap_percentile_95": [
          0.0,
          0.0
        ],
        "bootstrap_seed": 20261006,
        "bootstrap_replicates": 10000,
        "interpretation": "descriptive only; eight original development tasks do not establish quality superiority, equivalence or generalization"
      },
      "fault_arm": null,
      "analysis_sha256": "048449273f41e360099a185bcbfbfbf42c232ae226da4f0f4ee9b2dea7fb0b56",
      "development_declaration_sha256": "a3db16da78c15ece4bdd87b06e832d3dc3f15078adcadca2371415787861704f",
      "closure_envelope_sha256": "a671a263397908a4e80c45b3b49c08076b8c2dff1a13e369248c081c1e89bcf8",
      "interpretation": "Explicit argument/schema/batch-validation revision on the same exposed fixtures; do not pool, repair V1, or interpret V1-to-V2 change as an isolated causal gain."
    }
  }
}
