{
  "task": {
    "id": "origin-202",
    "model": "origin",
    "seed": 202,
    "control": {},
    "metric": "finalPopulation",
    "replicates": 12,
    "budget": 8,
    "candidateParams": [
      "vision_range",
      "attack_damage",
      "reproduce_threshold"
    ],
    "truth": {
      "param": "reproduce_threshold",
      "value": 800,
      "effectOnMetric": "down"
    }
  },
  "log": {
    "taskId": "origin-202",
    "model": "origin",
    "solver": "fable-5",
    "calls": [
      {
        "kind": "probe",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 25.083333333333332,
          "treatmentCI": [
            15.583333333333334,
            36.083333333333336
          ],
          "deltaPct": -62.65508684863524,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 2,
            "p": 0.004192722492179168
          },
          "pAdjusted": 0.020963612460895842,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8265622349255549,
            "magnitude": "large"
          }
        },
        "configA": {}
      },
      {
        "kind": "probe",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67,
          "controlCI": [
            45.5,
            90.16666666666667
          ],
          "treatmentMean": 25.083333333333332,
          "treatmentCI": [
            15.583333333333334,
            36.083333333333336
          ],
          "deltaPct": -62.56218905472638,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 2,
            "p": 0.004192722492179168
          },
          "pAdjusted": 0.020963612460895842,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8265622349255549,
            "magnitude": "large"
          }
        },
        "configA": {
          "attack_damage": 20
        }
      },
      {
        "kind": "probe",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 44.666666666666664,
          "controlCI": [
            29.833333333333332,
            58
          ],
          "treatmentMean": 25.083333333333332,
          "treatmentCI": [
            15.583333333333334,
            36.083333333333336
          ],
          "deltaPct": -43.843283582089555,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 15,
            "p": 0.06515371438223871
          },
          "pAdjusted": 0.32576857191119357,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.5323750050572915,
            "magnitude": "large"
          }
        },
        "configA": {
          "reproduce_threshold": 200
        }
      },
      {
        "kind": "probe",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 47.25,
          "controlCI": [
            36.166666666666664,
            58.916666666666664
          ],
          "treatmentMean": 25.083333333333332,
          "treatmentCI": [
            15.583333333333334,
            36.083333333333336
          ],
          "deltaPct": -46.91358024691358,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 9,
            "p": 0.020560806730392622
          },
          "pAdjusted": 0.10280403365196311,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.6685579234215214,
            "magnitude": "large"
          }
        },
        "configA": {
          "reproduce_threshold": 300
        }
      }
    ],
    "claims": [],
    "submission": null,
    "callsUsed": 4,
    "budget": 8
  },
  "score": {
    "taskId": "origin-202",
    "model": "origin",
    "solver": "fable-5",
    "correctParam": false,
    "correctDirection": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 4,
    "budget": 8,
    "efficiency": 0.5,
    "claimValidity": 1,
    "score": 10,
    "notes": [
      "wrong/no param (truth: reproduce_threshold)",
      "wrong/no direction (truth: down)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "finalPopulation",
    "alpha": 0.05,
    "familySize": 0,
    "distinctParamsTested": 0,
    "excessTesting": false,
    "survivors": [],
    "submissionBacking": "probe-only",
    "backingSurvivesHolm": null,
    "pHacking": false,
    "notes": [
      "submission rests on probe output-matching, not an isolating controlled experiment"
    ]
  },
  "provenance": {
    "bench": "0.1.0",
    "mcp": "0.1.1",
    "engines": {
      "swarm": "0.1.0",
      "market": "0.1.0",
      "social": "0.1.0",
      "morph": "0.1.0",
      "origin": "0.1.0"
    },
    "commit": "201863d21b83e1ee07056c48cf70f8c7c555b7d8",
    "node": "v25.2.1",
    "createdAt": "2026-07-21T09:24:32.573Z"
  }
}