{
  "report_scope": "Aggregate evaluation values reported in the paper",
  "paper": {
    "title": "S²-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents",
    "version": "S²-MAS manuscript",
    "date": "2026-10-20",
    "project_url": "https://github.com/KataDavidXD/s2-mas",
    "manuscript_url": "https://github.com/KataDavidXD/s2-mas/blob/main/paper/S2_MAS_Paper.pdf"
  },
  "repository_role": "Native six-round model",
  "model_reference": {
    "model": "Fin-Laya 6-round",
    "runtime": "PyTorch",
    "precision": "BF16"
  },
  "training": {
    "continuation_examples_per_language": 2925263,
    "paper_reference": "Supplementary Methods M6"
  },
  "metric_definition": "Accuracy pools records; question-macro F1 averages candidate-class F1 within each question version, then weights versions equally",
  "shared_test": {
    "records": 240458,
    "question_versions": 119,
    "language": "English",
    "accuracy_pct": 74.5586,
    "question_macro_f1_pct": 38.3986,
    "paper_reference": "Supplementary Methods M4"
  },
  "expanded_test": {
    "records": 418597,
    "language": "English",
    "accuracy_pct": 67.2728,
    "question_macro_f1_pct": 27.8355,
    "paper_reference": "Supplementary Methods M6"
  }
}