{
  "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": "ofat-rand",
    "calls": [
      {
        "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
        }
      },
      {
        "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": 0.7950946969255804,
          "treatmentCI": [
            0.6807107996761163,
            0.8905539250028743
          ],
          "deltaPct": -8.3379042915631,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 20,
            "p": 0.14670772297030288
          },
          "pAdjusted": 0.6304479584094458,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.41894250263350047,
            "magnitude": "medium"
          }
        },
        "configA": {},
        "configB": {
          "noise": 0.13539945567026734
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.8250342672851928,
          "treatmentCI": [
            0.7438378814825323,
            0.895394261905047
          ],
          "deltaPct": -4.886335850239272,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 26,
            "p": 0.3267995636020937
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.28306925853614895,
            "magnitude": "small"
          }
        },
        "configA": {},
        "configB": {
          "alignmentWeight": 1.378503127489239
        }
      }
    ],
    "claims": [
      {
        "param": "count",
        "effect": "down"
      },
      {
        "param": "maxForce",
        "effect": "none"
      },
      {
        "param": "noise",
        "effect": "none"
      },
      {
        "param": "alignmentWeight",
        "effect": "none"
      }
    ],
    "submission": null,
    "callsUsed": 4,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-101-l3",
    "model": "swarm",
    "solver": "ofat-rand",
    "correctParam": false,
    "correctDirection": false,
    "correctParams": false,
    "correctInteraction": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 4,
    "budget": 8,
    "efficiency": 0.5,
    "claimValidity": 1,
    "score": 10,
    "notes": [
      "wrong/no params (truth: alignmentWeight + noise)",
      "wrong/no interaction sign (truth: negative)",
      "not backed by a 2x2 factorial (isolate each param + a combined experiment)"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 4,
    "distinctParamsTested": 4,
    "excessTesting": false,
    "survivors": [
      "count"
    ],
    "submissionBacking": "none",
    "backingSurvivesHolm": null,
    "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": "2026-06-12T17:33:53.093Z"
  }
}