{
  "task": {
    "id": "swarm-202-l2",
    "model": "swarm",
    "seed": 202,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "tier": "L2",
    "candidateParams": [
      "alignmentWeight",
      "count",
      "maxForce"
    ],
    "truth": {
      "param": "alignmentWeight",
      "value": 0.2471,
      "effectOnMetric": "down",
      "magnitude": "small"
    }
  },
  "log": {
    "taskId": "swarm-202-l2",
    "model": "swarm",
    "solver": "gemini-3.1-pro",
    "calls": [
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": -29.412137023457202,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 5,
            "p": 0.008590034259602142
          },
          "pAdjusted": 0.025770102778806425,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.7586256128768792,
            "magnitude": "large"
          }
        },
        "configA": {}
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.7605484216242396,
          "treatmentCI": [
            0.7047157152236894,
            0.8091610959563447
          ],
          "deltaPct": -12.320554415234971,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 11,
            "p": 0.03098393885741535
          },
          "pAdjusted": 0.1239357554296614,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.6227523687795277,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "alignmentWeight": 0.7
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.5071662543805358,
          "treatmentCI": [
            0.3939956626214454,
            0.6148555031196169
          ],
          "deltaPct": -41.5315912319947,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 1,
            "p": 0.003263853493157942
          },
          "pAdjusted": 0.012631563477234486,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8492077756084468,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "count": 150
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.34319191381101727,
          "treatmentCI": [
            0.22680233159274935,
            0.47334156185057946
          ],
          "deltaPct": -60.435291328510175,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.012631563477234486,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "maxForce": 0.01
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.29882315839466733,
          "treatmentCI": [
            0.21944611697405167,
            0.37588145797440714
          ],
          "deltaPct": -65.55032117484602,
          "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": {},
        "configB": {
          "count": 100,
          "alignmentWeight": 1,
          "maxForce": 0.02
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.4501120492248438,
          "treatmentCI": [
            0.36835298930415306,
            0.5469618415481149
          ],
          "deltaPct": -48.1090568266864,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.012631563477234486,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "count": 135
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.5930478115317518,
          "treatmentCI": [
            0.4710963481511807,
            0.7065112937173555
          ],
          "deltaPct": -31.630778735541625,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 6,
            "p": 0.010787498143210783
          },
          "pAdjusted": 0.053937490716053915,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.7359800721939872,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "alignmentWeight": 0.4
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5930478115317518,
          "controlCI": [
            0.4672267133698968,
            0.7090102397812208
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": 3.245088463860826,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 38,
            "p": 0.9687122910210344
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.01132277034144596,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "alignmentWeight": 0.4
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "alignmentWeight",
      "direction": "down",
      "magnitude": "small"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202-l2",
    "model": "swarm",
    "solver": "gemini-3.1-pro",
    "correctParam": true,
    "correctDirection": true,
    "correctMagnitude": true,
    "solved": true,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 60,
    "notes": [
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 5,
    "distinctParamsTested": 3,
    "excessTesting": true,
    "survivors": [
      "alignmentWeight",
      "count",
      "maxForce"
    ],
    "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": "f305d9d54670c03a92b2c93b76040e15a5bc1840",
    "node": "v25.2.1",
    "createdAt": "2026-06-11T07:56:33.337Z"
  }
}