outputs/claim3.json

{
  "all_registered_statistics_match": true,
  "assessment": "verified",
  "claim": 3,
  "computed_median": 59622,
  "destructive_control_detected": true,
  "destructive_control_drop_one_domain_median": 81144.0,
  "domain_count": 10,
  "literal_claim": "Across the 10 domains used in the main evaluation, per-domain task counts range from 900 (Greenhouse Gas Prediction) to 426,043,800 (On-Policy RL), with a median of 59,622 tasks per domain (Table 1).",
  "maximum": {
    "b": 3,
    "d": 13,
    "domain": "On-Policy RL",
    "m": 4,
    "reported_tasks": 426043800
  },
  "minimum": {
    "b": 1,
    "d": 4,
    "domain": "Greenhouse Gas Prediction",
    "m": 2,
    "reported_tasks": 900
  },
  "reported_median": 59622
}