{
  "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": "opus-4.8",
    "calls": [
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.6235176925681029,
          "treatmentCI": [
            0.49707883801184366,
            0.7280056776858638
          ],
          "deltaPct": -28.118073692257816,
          "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": {},
        "configB": {
          "noise": 1
        }
      },
      {
        "kind": "experiment",
        "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": {},
        "configB": {
          "alignmentWeight": 0.2
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.25439562833717966,
          "controlCI": [
            0.19020663486755343,
            0.3143306449208672
          ],
          "treatmentMean": 0.6235176925681029,
          "treatmentCI": [
            0.49707883801184366,
            0.7280056776858638
          ],
          "deltaPct": 145.097644422444,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 2,
            "p": 0.004192722492179168
          },
          "pAdjusted": 0.012631563477234486,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.8265622349255549,
            "magnitude": "large"
          }
        },
        "configA": {
          "noise": 1,
          "alignmentWeight": 0.2
        }
      },
      {
        "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": 10
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.3164197998715762,
          "controlCI": [
            0.24395726198790238,
            0.3870811803388363
          ],
          "treatmentMean": 0.6235176925681029,
          "treatmentCI": [
            0.49707883801184366,
            0.7280056776858638
          ],
          "deltaPct": 97.05394315436865,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 3,
            "p": 0.005355381445612206
          },
          "pAdjusted": 0.012631563477234486,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.8039166942426631,
            "magnitude": "large"
          }
        },
        "configA": {
          "count": 10,
          "alignmentWeight": 0.2
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.30281749077482273,
          "controlCI": [
            0.23402054401407565,
            0.37544527351232587
          ],
          "treatmentMean": 0.6235176925681029,
          "treatmentCI": [
            0.49707883801184366,
            0.7280056776858638
          ],
          "deltaPct": 105.90544191245384,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 2,
            "p": 0.004192722492179168
          },
          "pAdjusted": 0.012631563477234486,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.8265622349255549,
            "magnitude": "large"
          }
        },
        "configA": {
          "noise": 1,
          "count": 10
        }
      },
      {
        "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": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.33758942350413873,
          "controlCI": [
            0.27074848940166985,
            0.39577509464326965
          ],
          "treatmentMean": 0.6235176925681029,
          "treatmentCI": [
            0.49707883801184366,
            0.7280056776858638
          ],
          "deltaPct": 84.69704592521357,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 6,
            "p": 0.010787498143210783
          },
          "pAdjusted": 0.04314999257284313,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.7359800721939872,
            "magnitude": "large"
          }
        },
        "configA": {
          "noise": 1,
          "maxForce": 0.1
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "alignmentWeight",
      "param2": "maxForce",
      "interaction": "positive"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202-l3",
    "model": "swarm",
    "solver": "opus-4.8",
    "correctParam": false,
    "correctDirection": false,
    "correctParams": false,
    "correctInteraction": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 12,
    "notes": [
      "only one of two params (truth: noise + alignmentWeight)",
      "wrong/no interaction sign (truth: negative)",
      "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",
      "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": "2f69869d52474b7d7f131299de3a4ffaa0b0b661",
    "node": "v25.2.1",
    "createdAt": "2026-06-11T04:54:30.364Z"
  }
}