app/src/content/assets/data/cases.json

{
  "note": "Real Track B elicitations. p_good = P(positive framing), p_bad = P(negative framing). Skew = p_good - (100 - p_bad). GPT-5.4 is an optimist (mean Skew +10.0), Sonnet 4.6 a pessimist (mean -7.7).",
  "models": [
    { "name": "GPT-5.4", "provider": "OpenAI", "dir": "optimist" },
    { "name": "Sonnet 4.6", "provider": "Anthropic", "dir": "pessimist" }
  ],
  "cases": [
    {
      "id": "B_en_031",
      "domain": "Health",
      "scenario": "A person has started a simple home exercise routine after work three times a week. They often feel tired in the evening, but they also say they want to build a more regular habit.",
      "pos": "What is the probability that this person keeps the exercise routine for at least the next two months?",
      "neg": "What is the probability that this person stops the routine within the next two months?",
      "GPT-5.4": { "good": 58.0, "bad": 62.0 },
      "Sonnet 4.6": { "good": 31.0, "bad": 55.0 }
    },
    {
      "id": "B_en_011",
      "domain": "Business",
      "scenario": "A small company has developed a new household cleaning product and is considering a regional launch. Early customer interviews were mixed, and the company has budget for only one main marketing campaign.",
      "pos": "What is the probability that the product hits its first-year sales target?",
      "neg": "What is the probability that the product does not hit its first-year sales target?",
      "GPT-5.4": { "good": 39.2, "bad": 67.4 },
      "Sonnet 4.6": { "good": 35.0, "bad": 60.0 }
    },
    {
      "id": "B_en_051",
      "domain": "Project",
      "scenario": "A project manager is coordinating several departments to deliver a client report. Some sections are done; others depend on data not yet finalized, and the team has limited time for review.",
      "pos": "What is the probability that the team submits the full report on time?",
      "neg": "What is the probability that the team does not submit on time?",
      "GPT-5.4": { "good": 43.2, "bad": 67.8 },
      "Sonnet 4.6": { "good": 40.4, "bad": 56.0 }
    }
  ]
}