{
  "task": {
    "id": "market-202-l2",
    "model": "market",
    "seed": 202,
    "control": {},
    "metric": "volatility",
    "replicates": 12,
    "budget": 8,
    "tier": "L2",
    "candidateParams": [
      "lambda",
      "fundFrac",
      "phiC"
    ],
    "truth": {
      "param": "phiC",
      "value": 44,
      "effectOnMetric": "up",
      "magnitude": "large"
    }
  },
  "log": {
    "taskId": "market-202-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": 0.014173505200309251,
          "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": 1.5
        }
      },
      {
        "kind": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.0015843298903487296,
          "treatmentCI": [
            0.0014924171493387723,
            0.001676242631358687
          ],
          "deltaPct": -31.92157186837366,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 143,
            "p": 0.00004697310620960238
          },
          "pAdjusted": 0.0008455159117728428,
          "significant": true,
          "effect": {
            "name": "Cliff's delta",
            "value": 0.9861111111111112,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "phiC": 1.5
        }
      },
      {
        "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": 1.5
        }
      },
      {
        "kind": "probe",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.0015843298903487296,
          "controlCI": [
            0.0014924171493387723,
            0.001676242631358687
          ],
          "treatmentMean": 0.07006508696360793,
          "treatmentCI": [
            0.01615789572643215,
            0.12397227820078371
          ],
          "deltaPct": 4322.379921657968,
          "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": 1.5
        }
      },
      {
        "kind": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.0014951095335801383,
          "treatmentCI": [
            0.0014025824504728523,
            0.0015876366166874243
          ],
          "deltaPct": -35.7553578009307,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 144,
            "p": 0.00003660522347836981
          },
          "pAdjusted": 0.0006461399206001417,
          "significant": true,
          "effect": {
            "name": "Cliff's delta",
            "value": 1,
            "magnitude": "large"
          }
        },
        "configA": {},
        "configB": {
          "phiC": 0.5
        }
      },
      {
        "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": "experiment",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.002327212795344664,
          "controlCI": [
            0.00212110742919089,
            0.0025333181614984384
          ],
          "treatmentMean": 0.0023844370496218198,
          "treatmentCI": [
            0.002276603700016366,
            0.0024922703992272736
          ],
          "deltaPct": 2.4589179980286486,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 64,
            "p": 0.6650054001531291
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "Cliff's delta",
            "value": -0.1111111111111111,
            "magnitude": "negligible"
          }
        },
        "configA": {},
        "configB": {
          "fundFrac": 0.5
        }
      },
      {
        "kind": "probe",
        "metric": "volatility",
        "stats": {
          "metric": "volatility",
          "label": "Volatility (return std)",
          "controlMean": 0.0032975015373722365,
          "controlCI": [
            0.0031989031554426435,
            0.0033960999193018296
          ],
          "treatmentMean": 0.07006508696360793,
          "treatmentCI": [
            0.01615789572643215,
            0.12397227820078371
          ],
          "deltaPct": 2024.793155348836,
          "test": {
            "name": "Mann-Whitney U (rank-sum)",
            "statistic": 65,
            "p": 0.7074538580073833
          },
          "pAdjusted": 1,
          "significant": false,
          "effect": {
            "name": "Cliff's delta",
            "value": -0.09722222222222222,
            "magnitude": "negligible"
          }
        },
        "configA": {
          "fundFrac": 0.1
        }
      }
    ],
    "claims": [],
    "submission": {
      "param": "fundFrac",
      "direction": "down",
      "magnitude": "large"
    },
    "callsUsed": 8,
    "budget": 8
  },
  "score": {
    "taskId": "market-202-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": [
      "phiC",
      "fundFrac"
    ],
    "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": "2026-06-11T06:13:33.188Z"
  }
}