{
  "citation": "QRData benchmark/eval.py at de450af45ff7101b328bb064c6b475f73414a7ed (Xiao Liu, Zirui Wu, Xueqing Wu, Pan Lu, Kai-Wei Chang, Yansong Feng. Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data. Findings of the Association for Computational Linguistics: ACL 2024, pages 9215-9235.)",
  "deviation_evidence": null,
  "doi": null,
  "excerpt": null,
  "independent": true,
  "item_set": null,
  "kind": "software",
  "known_deviation": null,
  "licence": "CC BY-NC 4.0",
  "locator": "benchmark/eval.py: extract_first_number, calc_acc",
  "metric": null,
  "n_items": null,
  "page": null,
  "read_copy_sha256": "d6e5c1f7535ac9413951996c15544beb6f184244acb2da56e1fcd0942837e33d",
  "retrieved_at": "2026-10-15",
  "se": null,
  "se_as_published": null,
  "source_id": "qrdata.eval_py",
  "tolerance_reason": null,
  "units": null,
  "url": "https://raw.githubusercontent.com/xxxiaol/QRData/de450af45ff7101b328bb064c6b475f73414a7ed/benchmark/eval.py",
  "value": null,
  "value_as_published": null,
  "verified_by": "benchmark_file",
  "verified_note": "Vendored byte for byte as suites/data/qrdata_socsci/vendor/benchmark_eval.py.txt; a parity test runs its functions against MAGI's port and the answer_figure_close check."
}