{
  "task": {
    "id": "swarm-202-l2",
    "model": "swarm",
    "seed": 202,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "tier": "L2",
    "candidateParams": [
      "alignmentWeight",
      "count",
      "maxForce"
    ],
    "truth": {
      "param": "alignmentWeight",
      "value": 0.2471,
      "effectOnMetric": "down",
      "magnitude": "small"
    }
  },
  "log": {
    "taskId": "swarm-202-l2",
    "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": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": -29.412137023457202,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 5,
            "p": 0.008590034259602142
          },
          "pAdjusted": 0.025770102778806425,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.7586256128768792,
            "magnitude": "large"
          }
        },
        "configA": {}
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.7237437701641234,
          "controlCI": [
            0.6502812895901184,
            0.7907861654559314
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": -15.399238944730659,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 25,
            "p": 0.28958747927122386
          },
          "pAdjusted": 0.8687624378136716,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.3057147992190409,
            "magnitude": "medium"
          }
        },
        "configA": {
          "alignmentWeight": 0.5
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.4908650929099632,
          "controlCI": [
            0.3987636372234751,
            0.5743309859269857
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": 24.737478075520308,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 18,
            "p": 0.10780181584888271
          },
          "pAdjusted": 0.10922681382431643,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.46423358399928427,
            "magnitude": "medium"
          }
        },
        "configA": {
          "alignmentWeight": 0.1
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.3854913682628493,
          "controlCI": [
            0.3170341167423972,
            0.4670050615268753
          ],
          "treatmentMean": 0.6122927376489478,
          "treatmentCI": [
            0.4911694720059983,
            0.7250678854224905
          ],
          "deltaPct": 58.83435740938634,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 10,
            "p": 0.025369775749057855
          },
          "pAdjusted": 0.05073955149811571,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.6453979094624196,
            "magnitude": "large"
          }
        },
        "configA": {
          "count": 50
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.365609246816889,
          "treatmentCI": [
            0.2888881686333323,
            0.4505134814297905
          ],
          "deltaPct": -57.850920269996564,
          "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": 75
        }
      },
      {
        "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": 0.5837363887509427,
          "treatmentCI": [
            0.48460064548503284,
            0.6781341122379901
          ],
          "deltaPct": -32.70424146824066,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 6,
            "p": 0.010787498143210783
          },
          "pAdjusted": 0.03236249442963235,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.7359800721939872,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "alignmentWeight": 0.3
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "alignmentWeight",
      "direction": "down",
      "magnitude": "small"
    },
    "callsUsed": 7,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202-l2",
    "model": "swarm",
    "solver": "gemini-3.1-pro",
    "correctParam": true,
    "correctDirection": true,
    "correctMagnitude": true,
    "solved": true,
    "withinBudget": true,
    "callsUsed": 7,
    "budget": 8,
    "efficiency": 0.125,
    "claimValidity": 1,
    "score": 86.9,
    "notes": []
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 3,
    "distinctParamsTested": 3,
    "excessTesting": false,
    "survivors": [
      "count",
      "maxForce",
      "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": "2026-06-11T20:18:42.818Z"
  }
}