src/about.py

TITLE = """
<h1 align="center">UniFFBench Leaderboard</h1>
<div align="center">
    <img src="https://raw.githubusercontent.com/M3RG-IITD/UniFFBench/main/uniff_logo.png" 
         width="80" style="margin: 10px 0;"/>
</div>
<p align="center">
    Benchmarking Universal Machine Learning Force Fields on the MinX-Datasets Mineral Dataset
</p>
<p align="center">
    📄 <a href="https://arxiv.org/abs/2508.05762">Paper</a> &nbsp;|&nbsp;
    💻 <a href="https://github.com/M3RG-IITD/UniFFBench">GitHub</a> &nbsp;|&nbsp;
    📦 <a href="https://huggingface.co/datasets/Sajid98/MinX-Datasets">Dataset</a>
</p>
"""

INTRODUCTION_TEXT = """
**UniFFBench** evaluates Universal Machine Learning Force Fields (UMLFFs)
against experimental measurements.

### To participate
1. Download the dataset from
   [Sajid98/MinX-Datasets](https://huggingface.co/datasets/Sajid98/MinX-Datasets).
2. Perform MD simulation using your own developed model. Follow the protocol used in UMLFF for MD simulations.
3. Compute the required benchmark metrics.
4. Upload your prediction CSV using the **Submit** tab.

"""
SUBMIT_INTRO = """
## 📤 How to Submit

1. Download the dataset.
2. Run your model locally.
3. Compute the required metrics.
4. Upload your prediction CSV using the Submit tab.

Submissions are reviewed before appearing on the leaderboard.
You will be notified by email once your submission is approved.
"""

CITATION_TEXT = """
## 📚 Citation

If you use UniFFBench, please cite:

@article{mannan2025evaluatinguniversalmachinelearning,
  title={Evaluating Universal Machine Learning Force Fields Against Experimental Measurements},
  author={Sajid Mannan and Vaibhav Bihani and Carmelo Gonzales and Kin Long Kelvin Lee and Nitya Nand Gosvami and Sayan Ranu and Santiago Miret and N. M. Anoop Krishnan},
  year={2025},
  eprint={2508.05762},
  archivePrefix={arXiv}
}
"""