{
  "task": {
    "id": "social-202-l3",
    "model": "social",
    "seed": 202,
    "control": {},
    "metric": "polarization",
    "replicates": 12,
    "budget": 8,
    "tier": "L3",
    "candidateParams": [
      "mu",
      "eps",
      "meanDeg",
      "k"
    ],
    "truth": {
      "param": "meanDeg",
      "value": 3,
      "effectOnMetric": "up",
      "param2": "eps",
      "value2": 0.08,
      "interaction": "negative"
    }
  },
  "log": {
    "taskId": "social-202-l3",
    "model": "social",
    "solver": "opus-4.8",
    "calls": [
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.5007675712198155,
          "controlCI": [
            0.4899638498495429,
            0.5121472305152566
          ],
          "treatmentMean": 0.029964426128572086,
          "treatmentCI": [
            0.024114828697444555,
            0.036276411905176546
          ],
          "deltaPct": -94.01630060517257,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.02021050156357518,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {
          "eps": 0.05
        },
        "configB": {
          "eps": 0.4
        }
      },
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.0942172593677242,
          "controlCI": [
            0.0733141981084676,
            0.11746990406221207
          ],
          "treatmentMean": 0.06848208585324757,
          "treatmentCI": [
            0.058633328995711054,
            0.07704143714108795
          ],
          "deltaPct": -27.31471249236175,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 18,
            "p": 0.10780181584888271
          },
          "pAdjusted": 0.754612710942179,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.46423358399928427,
            "magnitude": "medium"
          }
        },
        "configA": {
          "mu": 0.1
        },
        "configB": {
          "mu": 0.5
        }
      },
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.15037625745608238,
          "controlCI": [
            0.1256384800516874,
            0.17881963116305996
          ],
          "treatmentMean": 0.027641508448747725,
          "treatmentCI": [
            0.020113094610618037,
            0.036461631209628344
          ],
          "deltaPct": -81.61843570497126,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.02021050156357518,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {
          "meanDeg": 4
        },
        "configB": {
          "meanDeg": 20
        }
      },
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.0942172593677242,
          "controlCI": [
            0.0733141981084676,
            0.11746990406221207
          ],
          "treatmentMean": 0.06848208585324757,
          "treatmentCI": [
            0.058633328995711054,
            0.07704143714108795
          ],
          "deltaPct": -27.31471249236175,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 18,
            "p": 0.10780181584888271
          },
          "pAdjusted": 0.754612710942179,
          "significant": false,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.46423358399928427,
            "magnitude": "medium"
          }
        },
        "configA": {
          "k": 2
        },
        "configB": {
          "k": 10
        }
      },
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.0942172593677242,
          "controlCI": [
            0.0733141981084676,
            0.11746990406221207
          ],
          "treatmentMean": 0.021209793677553535,
          "treatmentCI": [
            0.013882092495138448,
            0.029019434719036022
          ],
          "deltaPct": -77.48842004120179,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.012438693106627818,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "eps": 0.4,
          "meanDeg": 20
        }
      },
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.0942172593677242,
          "controlCI": [
            0.0733141981084676,
            0.11746990406221207
          ],
          "treatmentMean": 0.029964426128572086,
          "treatmentCI": [
            0.024114828697444555,
            0.036276411905176546
          ],
          "deltaPct": -68.19645749657951,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.020133079879347093,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "eps": 0.4
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "eps",
      "param2": "meanDeg",
      "interaction": "positive"
    },
    "callsUsed": 6,
    "budget": 8
  },
  "score": {
    "taskId": "social-202-l3",
    "model": "social",
    "solver": "opus-4.8",
    "correctParam": true,
    "correctDirection": false,
    "correctParams": true,
    "correctInteraction": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 6,
    "budget": 8,
    "efficiency": 0.25,
    "claimValidity": 1,
    "score": 60,
    "notes": [
      "wrong/no interaction sign (truth: negative)"
    ]
  },
  "audit": {
    "metric": "polarization",
    "alpha": 0.05,
    "familySize": 5,
    "distinctParamsTested": 4,
    "excessTesting": true,
    "survivors": [
      "eps",
      "meanDeg"
    ],
    "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": "2026-06-11T05:13:46.681Z"
  }
}