updating arxiv link

app.py

@@ -267,7 +267,7 @@ Generative machine learning models hold great promise for accelerating materials
 
 **LeMat-GenBench** introduces a unified benchmark for generative models of crystalline materials, with standardized evaluation metrics** for meaningful model comparison, diverse tasks, and this leaderboard to encourage and track community progress.
 
-📄 **Paper**: [arXiv preprint](https://arxiv.org/abs/XXXX.XXXXX) | 💻 **Code**: [GitHub](https://github.com/LeMaterial/lemat-genbench) | 📧 **Contact**: siddharth.betala-ext [at] entalpic.ai, alexandre.duval [at] entalpic.ai
+📄 **Paper**: [arXiv](https://arxiv.org/abs/2512.04562) | 💻 **Code**: [GitHub](https://github.com/LeMaterial/lemat-genbench) | 📧 **Contact**: siddharth.betala-ext [at] entalpic.ai, alexandre.duval [at] entalpic.ai
 """)
         with gr.Tabs(elem_classes="tab-buttons"):
             with gr.TabItem("🚀 Leaderboard", elem_id="boundary-benchmark-tab-table"):