@article{whenimportancesamplingmisallocatescredit,
  title = {When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL},
  author = {Jiakang Wang and Runze Liu and Qingpeng Cai and Lei Lin and Wenping Hu and Xiu Li and Fuzheng Zhang and Guorui Zhou and Kun Gai and Ling Pan},
  year = {2025},
  eprint = {2510.06062},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.06062},
}