Updating arxiv link.

README.md

@@ -26,7 +26,7 @@ We provide weights for mimicking the temporal evolution of three different syste
 > **_Note_:** 
 > We provide each model based on two different O(3) backends: [e3nn](https://github.com/e3nn/e3nn) and [cuEquivariance](https://docs.nvidia.com/cuda/cuequivariance/). Choose the state dictionary and config.yaml dependent on whether you have CUDA and cuEquivariance installed. Please note that depending on the device used to initialize a model with the cuEquivariance backend, some parameter names may differ.
 
-Below we provide an overview of our architecture. For more information we refer to our [preprint](https://arxiv.org/) and [code](https://github.com/IBM/trajcast).
+Below we provide an overview of our architecture. For more information we refer to our [preprint](https://www.arxiv.org/abs/2503.23794) and [code](https://github.com/IBM/trajcast).
 
 <p align="center">
     <img src="arch.svg">
@@ -42,14 +42,14 @@ Below we provide an overview of our architecture. For more information we refer
 If you decide to use this dataset, please consider citing our preprint
 
 ```
-@misc{Thiemann2025Force-Free,
+@misc{thiemann2025Force-Free,
       title={Force-Free Molecular Dynamics Through Autoregressive Equivariant Networks}, 
-      author={Thiemann, Fabian L. and Reschützegger, Thiago, and Esposito, Massimiliano and Taddese, Tseden and Olarte-Plata, Juan D. and Martelli, Fausto},
+      author={Fabian L. Thiemann and Thiago Reschützegger and Massimiliano Esposito and Tseden Taddese and Juan D. Olarte-Plata and Fausto Martelli},
       year={2025},
-      eprint={...},
+      eprint={2503.23794},
       archivePrefix={arXiv},
-      primaryClass={...},
-      url={https://arxiv.org/...}, 
+      primaryClass={physics.comp-ph},
+      url={https://arxiv.org/abs/2503.23794}, 
 }
 ```