{
  "task": {
    "id": "swarm-202-l3",
    "model": "swarm",
    "seed": 202,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "tier": "L3",
    "candidateParams": [
      "noise",
      "alignmentWeight",
      "count",
      "maxForce"
    ],
    "truth": {
      "param": "noise",
      "value": 1,
      "effectOnMetric": "down",
      "param2": "alignmentWeight",
      "value2": 0.2,
      "interaction": "negative"
    }
  },
  "log": {
    "taskId": "swarm-202-l3",
    "model": "swarm",
    "solver": "sonnet-4.6",
    "calls": [
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.6805894488162251,
          "treatmentCI": [
            0.5861789682943871,
            0.7735612444394665
          ],
          "deltaPct": -21.538584728626102,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 1,
            "p": 0.003263853493157942
          },
          "pAdjusted": 0.013055413972631769,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8492077756084468,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "noise": 0.5
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.7237437701641234,
          "treatmentCI": [
            0.6506679812020234,
            0.787063307146926
          ],
          "deltaPct": -16.563560308366466,
          "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": {
          "alignmentWeight": 0.5
        }
      },
      {
        "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": 0.8084789675489615,
          "treatmentCI": [
            0.7498472902919037,
            0.8603032384118731
          ],
          "deltaPct": -6.794905326016225,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 21,
            "p": 0.16981061872831194
          },
          "pAdjusted": 0.6792424749132477,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.39629696195060854,
            "magnitude": "medium"
          }
        },
        "configA": {},
        "configB": {
          "maxForce": 0.5
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.35599794419923886,
          "treatmentCI": [
            0.2764461029805838,
            0.4286773677013498
          ],
          "deltaPct": -58.9589545001686,
          "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": {},
        "configB": {
          "noise": 0.5,
          "count": 50
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.5463038984798817,
          "treatmentCI": [
            0.4521664950180417,
            0.6484659987362361
          ],
          "deltaPct": -37.01962744565748,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 3,
            "p": 0.005355381445612206
          },
          "pAdjusted": 0.021421525782448825,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8039166942426631,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "noise": 0.5,
          "alignmentWeight": 0.5
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.38343072757997704,
          "treatmentCI": [
            0.31724115499328814,
            0.4460028031656367
          ],
          "deltaPct": -55.796379745844206,
          "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,
          "alignmentWeight": 0.5
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "count",
      "param2": "alignmentWeight",
      "interaction": "negative"
    },
    "callsUsed": 7,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202-l3",
    "model": "swarm",
    "solver": "sonnet-4.6",
    "correctParam": false,
    "correctDirection": false,
    "correctParams": false,
    "correctInteraction": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 7,
    "budget": 8,
    "efficiency": 0.125,
    "claimValidity": 1,
    "score": 39.5,
    "notes": [
      "only one of two params (truth: noise + alignmentWeight)",
      "not backed by a 2x2 factorial (isolate each param + a combined experiment)"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 4,
    "distinctParamsTested": 4,
    "excessTesting": false,
    "survivors": [
      "noise",
      "alignmentWeight",
      "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": "f305d9d54670c03a92b2c93b76040e15a5bc1840",
    "node": "v25.2.1",
    "createdAt": "2026-06-11T15:10:45.999Z"
  }
}