{
  "task": {
    "id": "swarm-101",
    "model": "swarm",
    "seed": 101,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "candidateParams": [
      "maxForce",
      "separationWeight",
      "count"
    ],
    "truth": {
      "param": "separationWeight",
      "value": 6,
      "effectOnMetric": "down"
    }
  },
  "log": {
    "taskId": "swarm-101",
    "model": "swarm",
    "solver": "ofat-rand",
    "calls": [
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.8137125104185796,
          "treatmentCI": [
            0.7344281097946109,
            0.8741833915777973
          ],
          "deltaPct": -6.191558945686838,
          "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": {},
        "configB": {
          "maxForce": 0.6595818586065434
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.7998237540503877,
          "treatmentCI": [
            0.7434286606337577,
            0.8552361079184334
          ],
          "deltaPct": -7.7927172987924465,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 21,
            "p": 0.16981061872831194
          },
          "pAdjusted": 0.33962123745662387,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.39629696195060854,
            "magnitude": "medium"
          }
        },
        "configA": {},
        "configB": {
          "separationWeight": 2.4719673874787986
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.628158411186797,
          "treatmentCI": [
            0.5381452024987764,
            0.7106887848322129
          ],
          "deltaPct": -27.583070760119675,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 2,
            "p": 0.004192722492179168
          },
          "pAdjusted": 0.016770889968716673,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8265622349255549,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "count": 482.25598802091554
        }
      }
    ],
    "claims": [
      {
        "param": "maxForce",
        "effect": "none"
      },
      {
        "param": "separationWeight",
        "effect": "none"
      },
      {
        "param": "count",
        "effect": "down"
      }
    ],
    "submission": {
      "param": "count",
      "direction": "down"
    },
    "callsUsed": 3,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-101",
    "model": "swarm",
    "solver": "ofat-rand",
    "correctParam": false,
    "correctDirection": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 3,
    "budget": 8,
    "efficiency": 0.625,
    "claimValidity": 1,
    "score": 32.5,
    "notes": [
      "wrong/no param (truth: separationWeight)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 3,
    "distinctParamsTested": 3,
    "excessTesting": false,
    "survivors": [
      "count"
    ],
    "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": "9a93d577a9e675a4ef200b7eaf8d0507b7fde39a",
    "node": "v25.2.1",
    "createdAt": "2026-06-12T17:30:50.659Z"
  }
}