{
  "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": "codex-gpt-5.5",
    "calls": [
      {
        "kind": "experiment",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.867419286871484,
          "controlCI": [
            0.8003408919082285,
            0.9186489587749551
          ],
          "treatmentMean": 0.6805894488162251,
          "treatmentCI": [
            0.5861789682943871,
            0.7735612444394665
          ],
          "deltaPct": -21.538584728626102,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 1,
            "p": 0.003263853493157942
          },
          "pAdjusted": 0.013055413972631769,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8492077756084468,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "noise": 0.5
        }
      },
      {
        "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": "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": 0.39193289254888725,
          "controlCI": [
            0.30501102719234474,
            0.4644802409445708
          ],
          "treatmentMean": 0.6235176925681029,
          "treatmentCI": [
            0.49707883801184366,
            0.7280056776858638
          ],
          "deltaPct": 59.08787050587472,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 12,
            "p": 0.03763275287182877
          },
          "pAdjusted": 0.03763275287182877,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.6001068280966357,
            "magnitude": "large"
          }
        },
        "configA": {
          "count": 100,
          "maxForce": 0.1
        }
      },
      {
        "kind": "probe",
        "metric": "avgOrder",
        "stats": {
          "metric": "avgOrder",
          "label": "Order parameter",
          "controlMean": 0.492427796517871,
          "controlCI": [
            0.4225991433241197,
            0.5633529054536291
          ],
          "treatmentMean": 0.6235176925681029,
          "treatmentCI": [
            0.49707883801184366,
            0.7280056776858638
          ],
          "deltaPct": 26.62114059710161,
          "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": {
          "noise": 0.5,
          "maxForce": 0.1
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "noise",
      "param2": "maxForce",
      "interaction": "positive"
    },
    "callsUsed": 6,
    "budget": 8
  },
  "score": {
    "taskId": "swarm-202-l3",
    "model": "swarm",
    "solver": "codex-gpt-5.5",
    "correctParam": true,
    "correctDirection": false,
    "correctParams": false,
    "correctInteraction": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 6,
    "budget": 8,
    "efficiency": 0.25,
    "claimValidity": 1,
    "score": 17,
    "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",
      "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": "f305d9d54670c03a92b2c93b76040e15a5bc1840",
    "node": "v25.2.1",
    "createdAt": "2026-06-11T06:54:00.808Z"
  }
}