eval_baselines_v2.json

{
  "grader_version": "v2_with_belief_accuracy",
  "note": "baselines emit no belief; belief_accuracy component is 0 for them by design",
  "indist": {
    "heuristic_mean": 0.4488,
    "random_mean": 0.402
  },
  "ood": {
    "heuristic_mean": 0.4539,
    "random_mean": 0.3974
  }
}