@inproceedings{zhou-etal-2026-repro,
    title = "{R}e{P}ro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of {LLM} Mathematical Problem Solving",
    author = "Zhou, Xiyuan  and
      Li, Zhuoqi  and
      Wang, Xinlei  and
      He, Yirui  and
      Wu, Yuhao  and
      Cheng, Yuheng  and
      Xu, Yan  and
      Zhao, Junhua  and
      Gu, Jinjin",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1322/",
    pages = "30112--30137",
    ISBN = "979-8-89176-459-0"
}