{
  "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": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.7237437701641234,
          "controlCI": [
            0.6502812895901184,
            0.7907861654559314
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": -15.399238944730659,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 25,
            "p": 0.28958747927122386
          },
          "pAdjusted": 0.8687624378136716,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.3057147992190409,
            "magnitude": "medium"
          }
        },
        "configA": {
          "alignmentWeight": 0.5
        }
      },
      {
        "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": 20
        }
      },
      {
        "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": 0.01
        }
      },
      {
        "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": 0.02
        }
      },
      {
        "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": 0.03
        }
      },
      {
        "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": 0.04
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5845744585057081,
          "controlCI": [
            0.44890679616651824,
            0.7115943565885529
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": 4.741616528045588,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 34,
            "p": 0.7240817810385578
          },
          "pAdjusted": 0.7240817810385578,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.10190493307301363,
            "magnitude": "small"
          }
        },
        "configA": {
          "maxForce": 0.1
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "maxForce",
      "direction": "down",
      "magnitude": "medium"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202-l2",
    "model": "swarm",
    "solver": "fable-5",
    "correctParam": false,
    "correctDirection": true,
    "correctMagnitude": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 25,
    "notes": [
      "wrong/no param (truth: alignmentWeight)",
      "magnitude off by one (said medium, truth small)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 0,
    "distinctParamsTested": 0,
    "excessTesting": false,
    "survivors": [],
    "submissionBacking": "probe-only",
    "backingSurvivesHolm": null,
    "pHacking": false,
    "notes": [
      "submission rests on probe output-matching, not an isolating controlled experiment"
    ]
  },
  "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": "2026-07-21T10:33:42.272Z"
  }
}