{
  "task": {
    "id": "swarm-101-l3",
    "model": "swarm",
    "seed": 101,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "tier": "L3",
    "candidateParams": [
      "count",
      "maxForce",
      "noise",
      "alignmentWeight"
    ],
    "truth": {
      "param": "alignmentWeight",
      "value": 0.2,
      "effectOnMetric": "down",
      "param2": "noise",
      "value2": 1,
      "interaction": "negative"
    }
  },
  "log": {
    "taskId": "swarm-101-l3",
    "model": "swarm",
    "solver": "opus-4.8",
    "calls": [
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.5361450274337375,
          "treatmentCI": [
            0.41242299026999224,
            0.6505219043248549
          ],
          "deltaPct": -38.19078782909605,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 1,
            "p": 0.003263853493157942
          },
          "pAdjusted": 0.012583174924591933,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8492077756084468,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "count": 200
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": -37.412294168313466,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.012583174924591933,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {}
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5361450274337375,
          "controlCI": [
            0.4127539712137032,
            0.6528861995093791
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": 1.2595107322028822,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 34,
            "p": 0.7240817810385578
          },
          "pAdjusted": 0.7240817810385578,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.10190493307301363,
            "magnitude": "small"
          }
        },
        "configA": {
          "count": 200
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5361450274337375,
          "controlCI": [
            0.4127539712137032,
            0.6528861995093791
          ],
          "treatmentMean": 0.5468930365064261,
          "treatmentCI": [
            0.45432008626684045,
            0.6436465543428034
          ],
          "deltaPct": 2.004683158982936,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 38,
            "p": 0.9687122910210344
          },
          "pAdjusted": 0.9687122910210344,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.01132277034144596,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "count": 200
        },
        "configB": {
          "count": 200,
          "alignmentWeight": 5
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.6805894488162251,
          "treatmentCI": [
            0.5861789682943871,
            0.7735612444394665
          ],
          "deltaPct": -21.538584728626102,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 1,
            "p": 0.003263853493157942
          },
          "pAdjusted": 0.013055413972631769,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8492077756084468,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "noise": 0.5
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5361450274337375,
          "controlCI": [
            0.4127539712137032,
            0.6528861995093791
          ],
          "treatmentMean": 0.5953137960787784,
          "treatmentCI": [
            0.4999739379295245,
            0.6836752929505541
          ],
          "deltaPct": 11.035963334072637,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 31,
            "p": 0.5562983636255043
          },
          "pAdjusted": 0.6535991272041874,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.16984155512168939,
            "magnitude": "small"
          }
        },
        "configA": {
          "count": 200
        },
        "configB": {
          "count": 200,
          "noise": 0.5
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.9155076469240181,
          "treatmentCI": [
            0.9005246578120681,
            0.9310280030797888
          ],
          "deltaPct": 5.543842612258962,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 30,
            "p": 0.5049030355991551
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.1924870958045813,
            "magnitude": "small"
          }
        },
        "configA": {},
        "configB": {
          "alignmentWeight": 5
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5468930365064261,
          "controlCI": [
            0.4524741744769624,
            0.6518349039019448
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": -0.7305276617727836,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 36,
            "p": 0.8445193049784514
          },
          "pAdjusted": 0.8996072872862477,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.056613851707229795,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "count": 200,
          "alignmentWeight": 5
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "count",
      "param2": "alignmentWeight",
      "interaction": "negative"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-101-l3",
    "model": "swarm",
    "solver": "opus-4.8",
    "correctParam": true,
    "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: alignmentWeight + noise)",
      "not backed by a 2x2 factorial (isolate each param + a combined experiment)"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 5,
    "distinctParamsTested": 3,
    "excessTesting": true,
    "survivors": [
      "count",
      "noise"
    ],
    "submissionBacking": "isolating-experiment",
    "backingSurvivesHolm": true,
    "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": "d86631b2d89b26b1472009e69619f41647f2f1fb",
    "node": "v25.2.1",
    "createdAt": "2026-06-12T14:23:48.232Z"
  }
}