{
  "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": "gemini-3.1-pro",
    "calls": [
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.6779028243650047,
          "treatmentCI": [
            0.5649070853188553,
            0.7867758841496538
          ],
          "deltaPct": -21.848310888959727,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 8,
            "p": 0.01672868299393193
          },
          "pAdjusted": 0.04314999257284313,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.6906889908282033,
            "magnitude": "large"
          }
        },
        "configA": {}
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.7813841362773427,
          "treatmentCI": [
            0.6810979957948953,
            0.8735628885279697
          ],
          "deltaPct": -9.918519439940484,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 17,
            "p": 0.09168047527646772
          },
          "pAdjusted": 0.3667219011058709,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.4868791246821762,
            "magnitude": "medium"
          }
        },
        "configA": {},
        "configB": {
          "separationWeight": 2
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.5845744585057081,
          "treatmentCI": [
            0.4600574003376547,
            0.713699320005487
          ],
          "deltaPct": -32.60762501441611,
          "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": 0.1
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.3854913682628493,
          "treatmentCI": [
            0.3166508709483477,
            0.4641061381668121
          ],
          "deltaPct": -55.55881981213505,
          "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": {
          "count": 50
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.8112781862211347,
          "treatmentCI": [
            0.7357978276040398,
            0.8765555912525339
          ],
          "deltaPct": -6.4721987970584625,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 28,
            "p": 0.41011687352557136
          },
          "pAdjusted": 0.6535991272041874,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.23777817717036512,
            "magnitude": "small"
          }
        },
        "configA": {},
        "configB": {
          "separationWeight": 3
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.7504038039727674,
          "treatmentCI": [
            0.6421892224465453,
            0.8469821440685928
          ],
          "deltaPct": -13.490071603175391,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 18,
            "p": 0.10780181584888271
          },
          "pAdjusted": 0.32340544754664813,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.46423358399928427,
            "magnitude": "medium"
          }
        },
        "configA": {},
        "configB": {
          "separationWeight": 0.5
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5647037058693156,
          "controlCI": [
            0.44311575964637545,
            0.6855449250818672
          ],
          "treatmentMean": 0.6779028243650047,
          "treatmentCI": [
            0.5649070853188553,
            0.7867758841496538
          ],
          "deltaPct": 20.045754493753183,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 19,
            "p": 0.12608959168188916
          },
          "pAdjusted": 0.12608959168188916,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.44158804331639234,
            "magnitude": "medium"
          }
        },
        "configA": {
          "maxForce": 0.08
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "maxForce",
      "direction": "down"
    },
    "callsUsed": 7,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-101",
    "model": "swarm",
    "solver": "gemini-3.1-pro",
    "correctParam": false,
    "correctDirection": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 7,
    "budget": 8,
    "efficiency": 0.125,
    "claimValidity": 1,
    "score": 22.5,
    "notes": [
      "wrong/no param (truth: separationWeight)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 5,
    "distinctParamsTested": 3,
    "excessTesting": true,
    "survivors": [
      "maxForce",
      "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": "b1010caca9edeebf446c741ad0df4d13591619bf",
    "node": "v25.2.1",
    "createdAt": "2026-06-10T19:06:35.312Z"
  }
}