{
  "task": {
    "id": "swarm-101-l2",
    "model": "swarm",
    "seed": 101,
    "control": {},
    "metric": "avgOrder",
    "replicates": 12,
    "budget": 8,
    "tier": "L2",
    "candidateParams": [
      "maxForce",
      "alignmentWeight",
      "count"
    ],
    "truth": {
      "param": "alignmentWeight",
      "value": 0.2416,
      "effectOnMetric": "down",
      "magnitude": "medium"
    }
  },
  "log": {
    "taskId": "swarm-101-l2",
    "model": "swarm",
    "solver": "codex-gpt-5.5",
    "calls": [
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.841842638569306,
          "treatmentCI": [
            0.7767624567650612,
            0.898146917741158
          ],
          "deltaPct": -2.948591147243812,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 25,
            "p": 0.28958747927122386
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.3057147992190409,
            "magnitude": "medium"
          }
        },
        "configA": {},
        "configB": {
          "alignmentWeight": 1.5
        }
      },
      {
        "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": 1.5
        }
      },
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.5071662543805358,
          "treatmentCI": [
            0.3939956626214454,
            0.6148555031196169
          ],
          "deltaPct": -41.5315912319947,
          "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": {
          "count": 150
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.5071662543805358,
          "controlCI": [
            0.39993065427876934,
            0.6259173531545237
          ],
          "treatmentMean": 0.5168490132129296,
          "treatmentCI": [
            0.3759621428206867,
            0.6562437744048878
          ],
          "deltaPct": 1.9091883083232004,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 36,
            "p": 0.8445193049784514
          },
          "pAdjusted": 0.8445193049784514,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.056613851707229795,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "count": 150
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "count",
      "direction": "up",
      "magnitude": "medium"
    },
    "callsUsed": 4,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-101-l2",
    "model": "swarm",
    "solver": "codex-gpt-5.5",
    "correctParam": false,
    "correctDirection": false,
    "correctMagnitude": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 4,
    "budget": 8,
    "efficiency": 0.5,
    "claimValidity": 1,
    "score": 27.5,
    "notes": [
      "wrong/no param (truth: alignmentWeight)",
      "wrong/no direction (truth: down)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "avgOrder",
    "alpha": 0.05,
    "familySize": 3,
    "distinctParamsTested": 3,
    "excessTesting": false,
    "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": "f305d9d54670c03a92b2c93b76040e15a5bc1840",
    "node": "v25.2.1",
    "createdAt": "2026-06-11T06:15:34.813Z"
  }
}