{
  "task": {
    "id": "origin-101-l3",
    "model": "origin",
    "seed": 101,
    "control": {},
    "metric": "finalPopulation",
    "replicates": 12,
    "budget": 8,
    "tier": "L3",
    "candidateParams": [
      "vision_range",
      "mutation_rate",
      "max_food",
      "move_cost"
    ],
    "truth": {
      "param": "move_cost",
      "value": 5,
      "effectOnMetric": "down",
      "param2": "max_food",
      "value2": 150,
      "interaction": "positive"
    }
  },
  "log": {
    "taskId": "origin-101-l3",
    "model": "origin",
    "solver": "ofat-rand",
    "calls": [
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 76.66666666666667,
          "treatmentCI": [
            60.583333333333336,
            92.5
          ],
          "deltaPct": 14.1439205955335,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 23,
            "p": 0.22365896734858937
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.35127619705198593,
            "magnitude": "medium"
          }
        },
        "configA": {},
        "configB": {
          "vision_range": 491.36170674231835
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 74.91666666666667,
          "treatmentCI": [
            61.75,
            92.58333333333333
          ],
          "deltaPct": 11.538461538461538,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 33,
            "p": 0.6661372645006556
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.12455047375590553,
            "magnitude": "small"
          }
        },
        "configA": {},
        "configB": {
          "mutation_rate": 0.734049332793802
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 68.83333333333333,
          "treatmentCI": [
            56,
            82.16666666666667
          ],
          "deltaPct": 2.4813895781637574,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 4,
            "p": 0.8551321567289785
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.09128709291752768,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "max_food": 1076.8957860022783
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 2.5833333333333335,
          "treatmentCI": [
            1.5,
            4
          ],
          "deltaPct": -96.15384615384616,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025166349849183867
          },
          "pAdjusted": 0.014926431727953382,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8721888380725838,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "move_cost": 9.311427772045135
        }
      }
    ],
    "claims": [
      {
        "param": "vision_range",
        "effect": "none"
      },
      {
        "param": "mutation_rate",
        "effect": "none"
      },
      {
        "param": "max_food",
        "effect": "none"
      },
      {
        "param": "move_cost",
        "effect": "down"
      }
    ],
    "submission": null,
    "callsUsed": 4,
    "budget": 8
  },
  "score": {
    "taskId": "origin-101-l3",
    "model": "origin",
    "solver": "ofat-rand",
    "correctParam": false,
    "correctDirection": false,
    "correctParams": false,
    "correctInteraction": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 4,
    "budget": 8,
    "efficiency": 0.5,
    "claimValidity": 1,
    "score": 10,
    "notes": [
      "wrong/no params (truth: move_cost + max_food)",
      "wrong/no interaction sign (truth: positive)",
      "not backed by a 2x2 factorial (isolate each param + a combined experiment)"
    ]
  },
  "audit": {
    "metric": "finalPopulation",
    "alpha": 0.05,
    "familySize": 4,
    "distinctParamsTested": 4,
    "excessTesting": false,
    "survivors": [
      "move_cost"
    ],
    "submissionBacking": "none",
    "backingSurvivesHolm": null,
    "pHacking": false,
    "notes": []
  },
  "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": "9a93d577a9e675a4ef200b7eaf8d0507b7fde39a",
    "node": "v25.2.1",
    "createdAt": "2026-06-12T17:34:39.056Z"
  }
}