{
  "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": "codex-gpt-5.5",
    "calls": [
      {
        "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": {},
        "configB": {
          "mu": 1
        }
      },
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.0942172593677242,
          "controlCI": [
            0.0733141981084676,
            0.11746990406221207
          ],
          "treatmentMean": 0.019661450743054348,
          "treatmentCI": [
            0.011564542942990858,
            0.028206561862801512
          ],
          "deltaPct": -79.1317950925351,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.01523464660236229,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": 0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "eps": 1
        }
      },
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.0942172593677242,
          "controlCI": [
            0.0733141981084676,
            0.11746990406221207
          ],
          "treatmentMean": 0.4424525048097469,
          "treatmentCI": [
            0.4154567186829808,
            0.47004515697711513
          ],
          "deltaPct": 369.60876147212247,
          "test": {
            "name": "Wilcoxon signed-rank",
            "statistic": 0,
            "p": 0.0025263126954468973
          },
          "pAdjusted": 0.013841063420833466,
          "significant": true,
          "effect": {
            "name": "rank-biserial r",
            "value": -0.8718533162913388,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "meanDeg": 1
        }
      },
      {
        "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": {},
        "configB": {
          "k": 1
        }
      },
      {
        "kind": "experiment",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.033231326515184866,
          "controlCI": [
            0.017366858447591463,
            0.049882658095642296
          ],
          "treatmentMean": 0.12315994291384418,
          "treatmentCI": [
            0.11040193214030293,
            0.13629360009435915
          ],
          "deltaPct": 270.6139833375804,
          "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": 1
        },
        "configB": {
          "eps": 1,
          "meanDeg": 1
        }
      },
      {
        "kind": "probe",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.11883159651551978,
          "controlCI": [
            0.10533521477264002,
            0.13350978684478226
          ],
          "treatmentMean": 0.21834994723309742,
          "treatmentCI": [
            0.19918629023110648,
            0.23698388214397711
          ],
          "deltaPct": 83.74738170296335,
          "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": 1,
          "meanDeg": 1
        }
      },
      {
        "kind": "probe",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.033231326515184866,
          "controlCI": [
            0.017366858447591463,
            0.049882658095642296
          ],
          "treatmentMean": 0.21834994723309742,
          "treatmentCI": [
            0.19918629023110648,
            0.23698388214397711
          ],
          "deltaPct": 557.0605814767089,
          "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": 1,
          "mu": 1
        }
      },
      {
        "kind": "probe",
        "metric": "polarization",
        "stats": {
          "metric": "polarization",
          "label": "Polarization Index",
          "controlMean": 0.43139046400453185,
          "controlCI": [
            0.40370333896256255,
            0.456210537464843
          ],
          "treatmentMean": 0.21834994723309742,
          "treatmentCI": [
            0.19918629023110648,
            0.23698388214397711
          ],
          "deltaPct": -49.38461429903012,
          "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": 1,
          "mu": 1
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "mu",
      "param2": "k",
      "interaction": "positive"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "social-202-l3",
    "model": "social",
    "solver": "codex-gpt-5.5",
    "correctParam": false,
    "correctDirection": false,
    "correctParams": false,
    "correctInteraction": false,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 0,
    "notes": [
      "wrong/no params (truth: meanDeg + eps)",
      "wrong/no interaction sign (truth: negative)",
      "not backed by a 2x2 factorial (isolate each param + a combined experiment)"
    ]
  },
  "audit": {
    "metric": "polarization",
    "alpha": 0.05,
    "familySize": 5,
    "distinctParamsTested": 4,
    "excessTesting": true,
    "survivors": [
      "eps",
      "meanDeg"
    ],
    "submissionBacking": "isolating-experiment",
    "backingSurvivesHolm": false,
    "pHacking": false,
    "notes": [
      "'mu' is significant alone but borderline: it does not survive family-wide Holm (low power, not over-testing)"
    ]
  },
  "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": "b1010caca9edeebf446c741ad0df4d13591619bf",
    "node": "v25.2.1",
    "createdAt": "2026-06-10T18:58:30.659Z"
  }
}