{
  "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": "codex-gpt-5.6-sol",
    "calls": [
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.8419308018115871,
          "treatmentCI": [
            0.790193087273166,
            0.8868321803917758
          ],
          "deltaPct": -2.9384272918147856,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 29,
            "p": 0.4561257049865399
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.21513263648747322,
            "magnitude": "small"
          }
        },
        "configA": {},
        "configB": {
          "alignmentWeight": 2
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.3821459443879634,
          "treatmentCI": [
            0.3160576895940052,
            0.46513207744320617
          ],
          "deltaPct": -55.944495335554855,
          "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": 100
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.3821459443879634,
          "controlCI": [
            0.3116062820320128,
            0.4622743236013997
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": 42.06557457097466,
          "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": 100
        }
      },
      {
        "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": 0.671188030172031,
          "treatmentCI": [
            0.5224235699667411,
            0.8080402870814357
          ],
          "deltaPct": -22.622422589564394,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 18,
            "p": 0.10780181584888271
          },
          "pAdjusted": 0.21560363169776542,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.46423358399928427,
            "magnitude": "medium"
          }
        },
        "configA": {},
        "configB": {
          "maxForce": 0.2
        }
      },
      {
        "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": 0.3854913682628493,
          "controlCI": [
            0.3170341167423972,
            0.4670050615268753
          ],
          "treatmentMean": 0.5428978315944375,
          "treatmentCI": [
            0.45591041503289437,
            0.6318495533484789
          ],
          "deltaPct": 40.83268168647029,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 15,
            "p": 0.06525713540351252
          },
          "pAdjusted": 0.06525713540351252,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.5321702060479601,
            "magnitude": "large"
          }
        },
        "configA": {
          "count": 50
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "count",
      "direction": "down"
    },
    "callsUsed": 7,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202",
    "model": "swarm",
    "solver": "codex-gpt-5.6-sol",
    "correctParam": false,
    "correctDirection": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 7,
    "budget": 8,
    "efficiency": 0.125,
    "claimValidity": 1,
    "score": 22.5,
    "notes": [
      "wrong/no param (truth: alignmentWeight)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 4,
    "distinctParamsTested": 3,
    "excessTesting": true,
    "survivors": [
      "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": "fd90d549028c1ae5ea80cf7e2c6f1343f450f5b5",
    "node": "v25.2.1",
    "createdAt": "2026-07-16T14:27:32.652Z"
  }
}