{
  "task": {
    "id": "swarm-101-l3",
    "model": "swarm",
    "seed": 101,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "tier": "L3",
    "candidateParams": [
      "count",
      "maxForce",
      "noise",
      "alignmentWeight"
    ],
    "truth": {
      "param": "alignmentWeight",
      "value": 0.2,
      "effectOnMetric": "down",
      "param2": "noise",
      "value2": 1,
      "interaction": "negative"
    }
  },
  "log": {
    "taskId": "swarm-101-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": 0.5361450274337375,
          "treatmentCI": [
            0.41242299026999224,
            0.6505219043248549
          ],
          "deltaPct": -38.19078782909605,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 1,
            "p": 0.003263853493157942
          },
          "pAdjusted": 0.012583174924591933,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8492077756084468,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "count": 200
        }
      },
      {
        "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": 0.5361450274337375,
          "controlCI": [
            0.4127539712137032,
            0.6528861995093791
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": 1.2595107322028822,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 34,
            "p": 0.7240817810385578
          },
          "pAdjusted": 0.7240817810385578,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.10190493307301363,
            "magnitude": "small"
          }
        },
        "configA": {
          "count": 200
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.08763116451902835,
          "treatmentCI": [
            0.06847064335207256,
            0.10743783832022576
          ],
          "deltaPct": -89.89748489048623,
          "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
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5361450274337375,
          "controlCI": [
            0.4127539712137032,
            0.6528861995093791
          ],
          "treatmentMean": 0.5384372426227862,
          "treatmentCI": [
            0.4350598820436496,
            0.6424523221348257
          ],
          "deltaPct": 0.42753640745685356,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 38,
            "p": 0.9687122910210344
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.01132277034144596,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "count": 200
        },
        "configB": {
          "count": 200,
          "maxForce": 1
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.876568467357894,
          "treatmentCI": [
            0.8440001583661267,
            0.9053263338066501
          ],
          "deltaPct": 1.0547587106816934,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 37,
            "p": 0.9063292973622197
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.03396831102433787,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "maxForce": 1
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5361450274337375,
          "controlCI": [
            0.4127539712137032,
            0.6528861995093791
          ],
          "treatmentMean": 0.12160604732805959,
          "treatmentCI": [
            0.09515678256834968,
            0.14665749026040517
          ],
          "deltaPct": -77.31844163320363,
          "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": {
          "count": 200
        },
        "configB": {
          "count": 200,
          "alignmentWeight": 0
        }
      },
      {
        "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": 5
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "count",
      "param2": "maxForce",
      "interaction": "negative"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-101-l3",
    "model": "swarm",
    "solver": "opus-4.8",
    "correctParam": false,
    "correctDirection": false,
    "correctParams": false,
    "correctInteraction": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 25,
    "notes": [
      "wrong/no params (truth: alignmentWeight + noise)",
      "not backed by a 2x2 factorial (isolate each param + a combined experiment)"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 6,
    "distinctParamsTested": 4,
    "excessTesting": true,
    "survivors": [
      "count",
      "alignmentWeight",
      "noise"
    ],
    "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": "2026-06-11T04:43:32.718Z"
  }
}