{
  "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": "haiku-4.5",
    "calls": [
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.4908650929099632,
          "controlCI": [
            0.3987636372234751,
            0.5743309859269857
          ],
          "treatmentMean": 0.8061472879627054,
          "treatmentCI": [
            0.7511492485466066,
            0.8531587268591098
          ],
          "deltaPct": 64.2299074851046,
          "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": 0.1
        },
        "configB": {
          "alignmentWeight": 0.9
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.3854913682628493,
          "controlCI": [
            0.3170341167423972,
            0.4670050615268753
          ],
          "treatmentMean": 0.3854913682628493,
          "treatmentCI": [
            0.3166508709483477,
            0.4641061381668121
          ],
          "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": {
          "count": 5
        },
        "configB": {
          "count": 20
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.8084789675489615,
          "controlCI": [
            0.7462443010534566,
            0.8584891541350589
          ],
          "treatmentMean": 0.876568467357894,
          "treatmentCI": [
            0.8440001583661267,
            0.9053263338066501
          ],
          "deltaPct": 8.421925930288213,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 20,
            "p": 0.14670772297030288
          },
          "pAdjusted": 0.5043583667275566,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.41894250263350047,
            "magnitude": "medium"
          }
        },
        "configA": {
          "maxForce": 0.5
        },
        "configB": {
          "maxForce": 3
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.7488381962639813,
          "controlCI": [
            0.6568999403200292,
            0.8285368446492969
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": -27.501316799409825,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 9,
            "p": 0.02065832536056611
          },
          "pAdjusted": 0.06197497608169833,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.6680434501453115,
            "magnitude": "large"
          }
        },
        "configA": {
          "alignmentWeight": 0.85
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.7237437701641234,
          "controlCI": [
            0.6502812895901184,
            0.7907861654559314
          ],
          "treatmentMean": 0.7488381962639813,
          "treatmentCI": [
            0.6600890414205275,
            0.8254972344021722
          ],
          "deltaPct": 3.4673080632068496,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 27,
            "p": 0.36698550577159494
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.260423717853257,
            "magnitude": "small"
          }
        },
        "configA": {
          "alignmentWeight": 0.5
        },
        "configB": {
          "alignmentWeight": 0.85
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "alignmentWeight",
      "direction": "up"
    },
    "callsUsed": 5,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202",
    "model": "swarm",
    "solver": "haiku-4.5",
    "correctParam": true,
    "correctDirection": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 5,
    "budget": 8,
    "efficiency": 0.375,
    "claimValidity": 1,
    "score": 67.5,
    "notes": [
      "wrong/no direction (truth: down)"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 4,
    "distinctParamsTested": 3,
    "excessTesting": true,
    "survivors": [
      "alignmentWeight"
    ],
    "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": "d86631b2d89b26b1472009e69619f41647f2f1fb",
    "node": "v25.2.1",
    "createdAt": "2026-06-12T02:13:41.142Z"
  }
}