{
  "task": {
    "id": "swarm-202",
    "model": "swarm",
    "seed": 202,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "candidateParams": [
      "alignmentWeight",
      "count",
      "maxForce"
    ],
    "truth": {
      "param": "alignmentWeight",
      "value": 0.2,
      "effectOnMetric": "down"
    }
  },
  "log": {
    "taskId": "swarm-202",
    "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": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": -37.412294168313466,
          "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": {}
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.08763116451902835,
          "controlCI": [
            0.06659616715434842,
            0.10865590349817078
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": 519.5259809386099,
          "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": {
          "alignmentWeight": 0
        }
      },
      {
        "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": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.7237437701641234,
          "controlCI": [
            0.6502812895901184,
            0.7907861654559314
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": -24.98756411107697,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 19,
            "p": 0.12608959168188916
          },
          "pAdjusted": 0.2521791833637783,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.44158804331639234,
            "magnitude": "medium"
          }
        },
        "configA": {
          "alignmentWeight": 0.5
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5845744585057081,
          "controlCI": [
            0.44890679616651824,
            0.7115943565885529
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": -7.129395803197525,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 32,
            "p": 0.6101201311587485
          },
          "pAdjusted": 0.6101201311587485,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.14719601443879746,
            "magnitude": "small"
          }
        },
        "configA": {
          "maxForce": 0.1
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "maxForce",
      "direction": "down"
    },
    "callsUsed": 6,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202",
    "model": "swarm",
    "solver": "gemini-3.1-pro",
    "correctParam": false,
    "correctDirection": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 6,
    "budget": 8,
    "efficiency": 0.25,
    "claimValidity": 1,
    "score": 25,
    "notes": [
      "wrong/no param (truth: alignmentWeight)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 2,
    "distinctParamsTested": 2,
    "excessTesting": false,
    "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": "2026-06-10T19:09:09.120Z"
  }
}