{
  "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": "fable-5",
    "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": 0.7237437701641234,
          "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": 0.5067005427855223,
          "controlCI": [
            0.3722288694483889,
            0.6509594147606422
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": 20.83917145281622,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 23,
            "p": 0.22401551029281253
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.3510058805848247,
            "magnitude": "medium"
          }
        },
        "configA": {
          "alignmentWeight": 0.25
        }
      },
      {
        "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": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.6544466599787636,
          "controlCI": [
            0.536703632412396,
            0.7693408368097542
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": -6.441154781229034,
          "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": {
          "alignmentWeight": 0.37
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.34319191381101727,
          "controlCI": [
            0.22907013478295055,
            0.46227294130921587
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": 78.41117841317032,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 8,
            "p": 0.01672868299393193
          },
          "pAdjusted": 0.03345736598786386,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.6906889908282033,
            "magnitude": "large"
          }
        },
        "configA": {
          "maxForce": 0.024
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.3854913682628493,
          "controlCI": [
            0.3170341167423972,
            0.4670050615268753
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": 58.83435740938634,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 10,
            "p": 0.025369775749057855
          },
          "pAdjusted": 0.05073955149811571,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.6453979094624196,
            "magnitude": "large"
          }
        },
        "configA": {
          "count": 30
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.867419286871484,
          "treatmentCI": [
            0.8050892275462198,
            0.920814761805557
          ],
          "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": {
          "alignmentWeight": 1
        }
      }
    ],
    "claims": [
      {
        "param": "alignmentWeight",
        "effect": "down"
      }
    ],
    "submission": {
      "param": "alignmentWeight",
      "direction": "down",
      "magnitude": "medium"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202-l2",
    "model": "swarm",
    "solver": "fable-5",
    "correctParam": true,
    "correctDirection": true,
    "correctMagnitude": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 75,
    "notes": [
      "magnitude off by one (said medium, truth small)"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 3,
    "distinctParamsTested": 2,
    "excessTesting": true,
    "survivors": [
      "alignmentWeight",
      "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": "2026-07-21T10:29:10.398Z"
  }
}