{
  "task": {
    "id": "swarm-101-l2",
    "model": "swarm",
    "seed": 101,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "tier": "L2",
    "candidateParams": [
      "maxForce",
      "alignmentWeight",
      "count"
    ],
    "truth": {
      "param": "alignmentWeight",
      "value": 0.2416,
      "effectOnMetric": "down",
      "magnitude": "medium"
    }
  },
  "log": {
    "taskId": "swarm-101-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": 0.5168490132129296,
          "treatmentCI": [
            0.3759621428206867,
            0.6562437744048878
          ],
          "deltaPct": -40.41531920773333,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 1,
            "p": 0.003263853493157942
          },
          "pAdjusted": 0.012631563477234486,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8492077756084468,
            "magnitude": "large"
          }
        },
        "configA": {}
      },
      {
        "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": "x0.5"
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.29882315839466733,
          "controlCI": [
            0.21128754110971482,
            0.37627199885381124
          ],
          "treatmentMean": 0.867419286871484,
          "treatmentCI": [
            0.8050892275462198,
            0.920814761805557
          ],
          "deltaPct": 190.2784682189356,
          "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": {
          "maxForce": 0.05,
          "alignmentWeight": 1,
          "count": 100
        },
        "configB": {}
      },
      {
        "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": 0.05
        },
        "configB": {}
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5845744585057081,
          "controlCI": [
            0.44890679616651824,
            0.7115943565885529
          ],
          "treatmentMean": 0.867419286871484,
          "treatmentCI": [
            0.8050892275462198,
            0.920814761805557
          ],
          "deltaPct": 48.38473940322078,
          "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": 0.1
        },
        "configB": {}
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5647037058693156,
          "controlCI": [
            0.44311575964637545,
            0.6855449250818672
          ],
          "treatmentMean": 0.5168490132129296,
          "treatmentCI": [
            0.3759621428206867,
            0.6562437744048878
          ],
          "deltaPct": -8.474301152799688,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 34,
            "p": 0.7240817810385578
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.10190493307301363,
            "magnitude": "small"
          }
        },
        "configA": {
          "maxForce": 0.08
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.671188030172031,
          "controlCI": [
            0.5165009179944325,
            0.803018311162238
          ],
          "treatmentMean": 0.867419286871484,
          "treatmentCI": [
            0.8050892275462198,
            0.920814761805557
          ],
          "deltaPct": 29.236405877076994,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 18,
            "p": 0.10780181584888271
          },
          "pAdjusted": 0.21560363169776542,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.46423358399928427,
            "magnitude": "medium"
          }
        },
        "configA": {
          "maxForce": 0.2
        },
        "configB": {}
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.7415912003631909,
          "controlCI": [
            0.6660556508222466,
            0.812388443266394
          ],
          "treatmentMean": 0.867419286871484,
          "treatmentCI": [
            0.8050892275462198,
            0.920814761805557
          ],
          "deltaPct": 16.967311161010176,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 8,
            "p": 0.01672868299393193
          },
          "pAdjusted": 0.08364341496965966,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.6906889908282033,
            "magnitude": "large"
          }
        },
        "configA": {
          "maxForce": 0.32
        },
        "configB": {}
      }
    ],
    "claims": [],
    "submission": {
      "param": "maxForce",
      "direction": "down",
      "magnitude": "large"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-101-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 large, truth medium)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 5,
    "distinctParamsTested": 2,
    "excessTesting": true,
    "survivors": [
      "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": "2026-07-21T10:20:05.013Z"
  }
}