Update README.md

README.md

@@ -101,13 +101,10 @@ tokenizer.apply_chat_template(question, add_generation_prompt=True)
 If you find this work useful in your research, please consider citing:
 
 ```bibtex
-@misc{lyu2025exploringlimitoutcomereward,
-      title={Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning}, 
-      author={Chengqi Lyu and Songyang Gao and Yuzhe Gu and Wenwei Zhang and Jianfei Gao and Kuikun Liu and Ziyi Wang and Shuaibin Li and Qian Zhao and Haian Huang and Weihan Cao and Jiangning Liu and Hongwei Liu and Junnan Liu and Songyang Zhang and Dahua Lin and Kai Chen},
-      year={2025},
-      eprint={2502.06781},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2502.06781}, 
+@article{lyu2025exploring,
+  title={Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning},
+  author={Lyu, Chengqi and Gao, Songyang and Gu, Yuzhe and Zhang, Wenwei and Gao, Jianfei and Liu, Kuikun and Wang, Ziyi and Li, Shuaibin and Zhao, Qian and Huang, Haian and others},
+  journal={arXiv preprint arXiv:2502.06781},
+  year={2025}
 }
 ```