Update README.md

README.md

@@ -22,7 +22,7 @@ This model was used in our first place submission to the [AIMO-2 Kaggle competit
 
 OpenMath-Nemotron models achieve state-of-the-art results on popular mathematical benchmarks. We present metrics as pass@1 (maj@64) where pass@1
 is an average accuracy across 64 generations and maj@64 is the result of majority voting. 
-Please see our [paper](https://github.com/NVIDIA/NeMo-Skills/blob/main/recipes/openmathreasoning.pdf) for more details on the evaluation setup.
+Please see our [paper](https://arxiv.org/abs/2504.16891) for more details on the evaluation setup.
 
 | Model                         | AIME24 |  AIME25     |  HMMT-24-25     | HLE-Math    |
 |-------------------------------|-----------------|-------|-------|-------------|
@@ -56,6 +56,7 @@ The pipeline we used to produce the data and models is fully open-sourced!
 - [Code](https://github.com/NVIDIA/NeMo-Skills)
 - [Models](https://huggingface.co/collections/nvidia/openmathreasoning-68072c0154a5099573d2e730)
 - [Dataset](https://huggingface.co/datasets/nvidia/OpenMathReasoning)
+- [Paper](https://arxiv.org/abs/2504.16891)
 
 We provide [all instructions](https://nvidia.github.io/NeMo-Skills/openmathreasoning1/)
 to fully reproduce our results, including data generation.
@@ -108,7 +109,7 @@ If you find our work useful, please consider citing us!
   title   = {AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset},
   author  = {Ivan Moshkov and Darragh Hanley and Ivan Sorokin and Shubham Toshniwal and Christof Henkel and Benedikt Schifferer and Wei Du and Igor Gitman},
   year    = {2025},
-  journal = {arXiv preprint arXiv:TBD}
+  journal = {arXiv preprint arXiv:2504.16891}
 }
 ```