{
  "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": "codex-gpt-5.6-sol",
    "calls": [
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 66.41666666666667,
          "treatmentCI": [
            55.333333333333336,
            78.75
          ],
          "deltaPct": -1.1166253101736971,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 36.5,
            "p": 0.8752816363643177
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.04530851106870566,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "vision_range": 6
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 67.16666666666667,
          "treatmentCI": [
            53.25,
            78.33333333333333
          ],
          "deltaPct": 0,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 38.5,
            "p": 0.9999999989503827
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "mutation_rate": 0.1
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 27,
          "treatmentCI": [
            11,
            46.583333333333336
          ],
          "deltaPct": -59.801488833746895,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 5.5,
            "p": 0.009605208947093047
          },
          "pAdjusted": 0.048026044735465234,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.7475904326336434,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "max_food": 200
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 67.16666666666667,
          "treatmentCI": [
            56.083333333333336,
            78.58333333333333
          ],
          "deltaPct": 0,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 1
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "move_cost": 0.1
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 67.16666666666667,
          "controlCI": [
            55.416666666666664,
            78.75
          ],
          "treatmentMean": 20,
          "treatmentCI": [
            6,
            42.25
          ],
          "deltaPct": -70.22332506203473,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 7,
            "p": 0.01347121390819317
          },
          "pAdjusted": 0.05388485563277268,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.7133345315110954,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "max_food": 200,
          "vision_range": 6
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 27,
          "controlCI": [
            9.833333333333334,
            46.833333333333336
          ],
          "treatmentMean": 46.583333333333336,
          "treatmentCI": [
            29.416666666666668,
            65.41666666666667
          ],
          "deltaPct": 72.53086419753087,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 18.5,
            "p": 0.11652384193315002
          },
          "pAdjusted": 0.6991430515989001,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.4530851106870566,
            "magnitude": "medium"
          }
        },
        "configA": {
          "max_food": 200
        },
        "configB": {
          "max_food": 200,
          "mutation_rate": 0.1
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 27,
          "controlCI": [
            9.833333333333334,
            46.833333333333336
          ],
          "treatmentMean": 20,
          "treatmentCI": [
            6,
            42.25
          ],
          "deltaPct": -25.925925925925924,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 29,
            "p": 0.4559523774727896
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.21521542757635187,
            "magnitude": "small"
          }
        },
        "configA": {
          "max_food": 200
        },
        "configB": {
          "max_food": 200,
          "vision_range": 6
        }
      },
      {
        "kind": "experiment",
        "metric": "finalPopulation",
        "stats": {
          "metric": "finalPopulation",
          "label": "Final Population",
          "controlMean": 27,
          "controlCI": [
            9.833333333333334,
            46.833333333333336
          ],
          "treatmentMean": 27,
          "treatmentCI": [
            11,
            46.583333333333336
          ],
          "deltaPct": 0,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 1
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "max_food": 200
        },
        "configB": {
          "max_food": 200,
          "move_cost": 0.1
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "max_food",
      "param2": "mutation_rate",
      "interaction": "positive"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "origin-101-l3",
    "model": "origin",
    "solver": "codex-gpt-5.6-sol",
    "correctParam": false,
    "correctDirection": false,
    "correctParams": false,
    "correctInteraction": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 37,
    "notes": [
      "only one of two params (truth: move_cost + max_food)",
      "not backed by a 2x2 factorial (isolate each param + a combined experiment)"
    ]
  },
  "audit": {
    "metric": "finalPopulation",
    "alpha": 0.05,
    "familySize": 7,
    "distinctParamsTested": 4,
    "excessTesting": true,
    "survivors": [],
    "submissionBacking": "isolating-experiment",
    "backingSurvivesHolm": false,
    "pHacking": true,
    "notes": [
      "'max_food' is significant alone but fails Holm across 7 episode tests, and the agent over-tested (7 tests for 4 params) — multiple-comparisons fishing"
    ]
  },
  "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": "9511c1d0a1e2d80b703e1550914605451af2fc08",
    "node": "v25.2.1",
    "createdAt": "2026-07-16T16:05:48.892Z"
  }
}