{
  "task": {
    "id": "swarm-202",
    "model": "swarm",
    "seed": 202,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "candidateParams": [
      "alignmentWeight",
      "count",
      "maxForce"
    ],
    "truth": {
      "param": "alignmentWeight",
      "value": 0.2,
      "effectOnMetric": "down"
    }
  },
  "log": {
    "taskId": "swarm-202",
    "model": "swarm",
    "solver": "fable-5",
    "calls": [
      {
        "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": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.08763116451902835,
          "treatmentCI": [
            0.06847064335207256,
            0.10743783832022576
          ],
          "deltaPct": -89.89748489048623,
          "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": {
          "alignmentWeight": 0
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.3854913682628493,
          "controlCI": [
            0.3170341167423972,
            0.4670050615268753
          ],
          "treatmentMean": 0.5697534563074538,
          "treatmentCI": [
            0.46792364114567847,
            0.6659957286699176
          ],
          "deltaPct": 47.79927728990404,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 8,
            "p": 0.01672868299393193
          },
          "pAdjusted": 0.02694242781638634,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.6906889908282033,
            "magnitude": "large"
          }
        },
        "configA": {
          "count": 30
        },
        "configB": {
          "count": 300
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.34319191381101727,
          "controlCI": [
            0.22907013478295055,
            0.46227294130921587
          ],
          "treatmentMean": 0.867419286871484,
          "treatmentCI": [
            0.8050892275462198,
            0.920814761805557
          ],
          "deltaPct": 152.75050255092515,
          "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": {
          "maxForce": 0.02
        },
        "configB": {
          "maxForce": 0.3
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5697534563074538,
          "controlCI": [
            0.47574300406672676,
            0.6570506482572256
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": -4.713551873307862,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 35,
            "p": 0.7836524311445308
          },
          "pAdjusted": 0.7836524311445308,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.07925939239012171,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "count": 300
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.7237437701641234,
          "treatmentCI": [
            0.6506679812020234,
            0.787063307146926
          ],
          "deltaPct": -16.563560308366466,
          "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": {
          "alignmentWeight": 0.5
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5837363887509427,
          "controlCI": [
            0.48162296498234886,
            0.6816225032173399
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": -6.996061568799919,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 31,
            "p": 0.5562983636255043
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.16984155512168939,
            "magnitude": "small"
          }
        },
        "configA": {
          "alignmentWeight": 0.3
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.45370217112281835,
          "controlCI": [
            0.3846152164283498,
            0.534656495219034
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": 19.659518104327883,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 20,
            "p": 0.14670772297030288
          },
          "pAdjusted": 0.29341544594060576,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.41894250263350047,
            "magnitude": "medium"
          }
        },
        "configA": {
          "count": 250
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "count",
      "direction": "down"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202",
    "model": "swarm",
    "solver": "fable-5",
    "correctParam": false,
    "correctDirection": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 20,
    "notes": [
      "wrong/no param (truth: alignmentWeight)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 4,
    "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": "201863d21b83e1ee07056c48cf70f8c7c555b7d8",
    "node": "v25.2.1",
    "createdAt": "2026-07-21T09:10:49.822Z"
  }
}