{
  "title": "American Flag VADER Known-Effect Evaluation",
  "version": "1.0.0",
  "seed": "conjoint-survey-american-flag-vader-v1",
  "generatedAt": "2026-08-17T20:51:44.533Z",
  "passed": true,
  "respondentCount": 1000,
  "permutations": 10000,
  "prompt": "What does being American mean to you?",
  "arms": [
    {
      "condition": "No image",
      "n": 500,
      "stimulus": null,
      "responseRule": "15% positive-pattern and 85% neutral-pattern synthetic language",
      "positivePatternN": 73,
      "positivePatternRate": 0.146
    },
    {
      "condition": "American flag",
      "n": 500,
      "stimulus": "american-flag.svg",
      "responseRule": "75% positive-pattern and 25% neutral-pattern synthetic language",
      "positivePatternN": 354,
      "positivePatternRate": 0.708
    }
  ],
  "passCriteria": {
    "treatmentMinusControlMinimum": 0.3,
    "confidenceIntervalMustExcludeZero": true,
    "exactArmSize": 500
  },
  "results": {
    "treatmentMean": 0.5430746000000007,
    "treatmentSd": 0.30550673804159767,
    "controlMean": 0.18078919999999984,
    "controlSd": 0.29936941764281755,
    "treatmentMinusControl": 0.36228540000000087,
    "standardError": 0.019128848120502032,
    "confidenceInterval95": [
      0.3247928576838169,
      0.39977794231618485
    ],
    "standardizedMeanDifference": 1.197821238171973,
    "permutationPValue": 0.00009999000099990002
  },
  "checks": [
    {
      "name": "exactly 500 synthetic responses were assigned to each arm",
      "passed": true
    },
    {
      "name": "treatment-minus-control sentiment exceeds the prespecified minimum",
      "passed": true
    },
    {
      "name": "the 95% confidence interval excludes zero",
      "passed": true
    },
    {
      "name": "the randomization-inference p-value is below 0.05",
      "passed": true
    },
    {
      "name": "all VADER compound scores remain in the documented range",
      "passed": true
    }
  ],
  "interpretation": "The evaluation tests whether the VADER scoring and treatment-comparison pipeline detects a sentiment difference deliberately encoded in synthetic responses. It does not estimate the effect of an American flag on real people."
}