update arXiv ID

README.md

@@ -26,7 +26,7 @@ This model investigates catastrophic forgetting when finetuning language models
 
 ## Quick Links
 
-- 📄 **Paper**: [arXiv](https://arxiv.org/abs/XXXX.XXXXX) *(to be updated after submission)*
+- 📄 **Paper**: [arXiv:2512.13706](https://arxiv.org/abs/2512.13706)
 - 💻 **Code**: [GitHub Repository](https://github.com/johngrahamreynolds/mathematical_catastrophe_mitigation)
 - 🤗 **Model Collection**: [All experiment checkpoints](https://huggingface.co/MarioBarbeque)
 
@@ -129,10 +129,10 @@ The complete training code, evaluation scripts, and experiment configurations ar
 If you use this model in your research, please cite:
 
 ```bibtex
-@article{reynolds2024catastrophic,
+@article{reynolds2025catastrophic,
   title={Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training},
   author={Reynolds, John Graham},
-  journal={arXiv preprint},
+  journal={arXiv preprint arXiv:2512.13706},
   year={2025},
   url={https://github.com/johngrahamreynolds/mathematical_catastrophe_mitigation}
 }