{
  "task": {
    "id": "market-101-l2",
    "model": "market",
    "seed": 101,
    "control": {},
    "metric": "volatility",
    "replicates": 12,
    "budget": 8,
    "tier": "L2",
    "candidateParams": [
      "fundFrac",
      "phiC",
      "lambda"
    ],
    "truth": {
      "param": "phiC",
      "value": 35,
      "effectOnMetric": "up",
      "magnitude": "large"
    }
  },
  "log": {
    "taskId": "market-101-l2",
    "model": "market",
    "solver": "codex-gpt-5.5",
    "calls": [
      {
        "kind": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.0014064748867556051,
          "treatmentCI": [
            0.0009708031779773773,
            0.001842146595533833
          ],
          "deltaPct": -39.56397586120595,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 117,
            "p": 0.010193159729763757
          },
          "pAdjusted": 0.13251107648692884,
          "significant": false,
          "effect": {
            "name": "Cliff's delta",
            "value": 0.625,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "fundFrac": 1.25
        }
      },
      {
        "kind": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.0015389591279289883,
          "treatmentCI": [
            0.0014400582359273303,
            0.0016378600199306462
          ],
          "deltaPct": -33.87114702155693,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 144,
            "p": 0.00003660522347836981
          },
          "pAdjusted": 0.0006588940226106565,
          "significant": true,
          "effect": {
            "name": "Cliff's delta",
            "value": 1,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "phiC": 1.25
        }
      },
      {
        "kind": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.014173505200309251,
          "treatmentCI": [
            -0.0017235257019337265,
            0.03007053610255223
          ],
          "deltaPct": 509.0334854063111,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 79,
            "p": 0.7074538580073833
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "Cliff's delta",
            "value": 0.09722222222222222,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "lambda": 1.25
        }
      },
      {
        "kind": "probe",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.0015389591279289883,
          "controlCI": [
            0.0014400582359273303,
            0.0016378600199306462
          ],
          "treatmentMean": 0.07182666569608415,
          "treatmentCI": [
            0.01647218435280772,
            0.12718114703936056
          ],
          "deltaPct": 4567.223735353056,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 0,
            "p": 0.00003660522347836981
          },
          "pAdjusted": 0.0006588940226106565,
          "significant": true,
          "effect": {
            "name": "Cliff's delta",
            "value": -1,
            "magnitude": "large"
          }
        },
        "configA": {
          "phiC": 1.25
        }
      },
      {
        "kind": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.001511542898630168,
          "treatmentCI": [
            0.0014456772485440445,
            0.0015774085487162913
          ],
          "deltaPct": -35.049218461936746,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 144,
            "p": 0.00003660522347836981
          },
          "pAdjusted": 0.0006588940226106565,
          "significant": true,
          "effect": {
            "name": "Cliff's delta",
            "value": 1,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "phiC": 0.75
        }
      },
      {
        "kind": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.014173505200309251,
          "treatmentCI": [
            -0.0017235257019337265,
            0.03007053610255223
          ],
          "deltaPct": 509.0334854063111,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 79,
            "p": 0.7074538580073833
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "Cliff's delta",
            "value": 0.09722222222222222,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "lambda": 2
        }
      },
      {
        "kind": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.014173505200309251,
          "treatmentCI": [
            -0.0017235257019337265,
            0.03007053610255223
          ],
          "deltaPct": 509.0334854063111,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 79,
            "p": 0.7074538580073833
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "Cliff's delta",
            "value": 0.09722222222222222,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "lambda": 0.5
        }
      },
      {
        "kind": "probe",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.0032975015373722365,
          "controlCI": [
            0.0031989031554426435,
            0.0033960999193018296
          ],
          "treatmentMean": 0.07182666569608415,
          "treatmentCI": [
            0.01647218435280772,
            0.12718114703936056
          ],
          "deltaPct": 2078.2147750967383,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 72,
            "p": 1
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "Cliff's delta",
            "value": 0,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "fundFrac": 0.25
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "fundFrac",
      "direction": "down",
      "magnitude": "large"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "market-101-l2",
    "model": "market",
    "solver": "codex-gpt-5.5",
    "correctParam": false,
    "correctDirection": false,
    "correctMagnitude": true,
    "solved": false,
    "withinBudget": true,
    "callsUsed": 8,
    "budget": 8,
    "efficiency": 0,
    "claimValidity": 1,
    "score": 20,
    "notes": [
      "wrong/no param (truth: phiC)",
      "wrong/no direction (truth: up)",
      "conclusion not backed by a significant isolating experiment"
    ]
  },
  "audit": {
    "metric": "volatility",
    "alpha": 0.05,
    "familySize": 6,
    "distinctParamsTested": 3,
    "excessTesting": true,
    "survivors": [
      "fundFrac",
      "phiC"
    ],
    "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": "155e0390345537b17507a5ce774cf119dff7dc56",
    "node": "v25.2.1",
    "createdAt": "2026-06-11T18:34:56.287Z"
  }
}