Update README.md

README.md

@@ -24,6 +24,8 @@ language:
 
 This model was introduced in the paper[*Surgical Post-Training: Cutting Errors, Keeping Knowledge* (Lin & Han, 2026)](https://arxiv.org/abs/2603.01683). 
 
+- **Code Repository:** [Visual-AI/SPoT](https://github.com/Visual-AI/SPoT)
+
 ## Training Details & Performance
 
 - **Efficiency:** The model was trained using merely **4k rectified math data pairs**. It avoids standard multi-phase pipelines (SFT → GRPO → DPO).
@@ -72,4 +74,19 @@ generated_ids =[
 ]
 
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-print(response)
+print(response)
+```
+
+## Citation
+
+If you find our model, data, or the SPoT methodology useful in your research, please consider citing our paper:
+
+**BibTeX:**
+```bibtex
+@article{lin2026surgical,
+      title={Surgical Post-Training: Cutting Errors, Keeping Knowledge}, 
+      author={Wenye Lin and Kai Han},
+      year={2026},
+      journal={arXiv preprint arXiv:2603.01683}
+}
+```