@article{reevaluatingcodellmbenchmarksunder,
  title = {Re-Evaluating Code LLM Benchmarks Under Semantic Mutation},
  author = {Zhiyuan Pan and Xing Hu and Xin Xia and Xiaohu Yang},
  year = {2025},
  eprint = {2506.17369},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.17369v1},
}