MLIP Arena: Advancing Fairness and Transparency in Machine Learning Interatomic Potentials via an Open, Accessible Benchmark Platform
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918199149199360 |
|---|---|
| author | Chiang, Yuan Kreiman, Tobias Zhang, Christine Kuner, Matthew C. Weaver, Elizabeth Amin, Ishan Park, Hyunsoo Lim, Yunsung Kim, Jihan Chrzan, Daryl Walsh, Aron Blau, Samuel M. Asta, Mark Krishnapriyan, Aditi S. |
| author_facet | Chiang, Yuan Kreiman, Tobias Zhang, Christine Kuner, Matthew C. Weaver, Elizabeth Amin, Ishan Park, Hyunsoo Lim, Yunsung Kim, Jihan Chrzan, Daryl Walsh, Aron Blau, Samuel M. Asta, Mark Krishnapriyan, Aditi S. |
| contents | Machine learning interatomic potentials (MLIPs) have revolutionized molecular and materials modeling, but existing benchmarks suffer from data leakage, limited transferability, and an over-reliance on error-based metrics tied to specific density functional theory (DFT) references. We introduce MLIP Arena, a benchmark platform that evaluates force field performance based on physics awareness, chemical reactivity, stability under extreme conditions, and predictive capabilities for thermodynamic properties and physical phenomena. By moving beyond static DFT references and revealing the important failure modes of current foundation MLIPs in real-world settings, MLIP Arena provides a reproducible framework to guide the next-generation MLIP development toward improved predictive accuracy and runtime efficiency while maintaining physical consistency. The Python package and online leaderboard are available at https://github.com/atomind-ai/mlip-arena. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20630 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MLIP Arena: Advancing Fairness and Transparency in Machine Learning Interatomic Potentials via an Open, Accessible Benchmark Platform Chiang, Yuan Kreiman, Tobias Zhang, Christine Kuner, Matthew C. Weaver, Elizabeth Amin, Ishan Park, Hyunsoo Lim, Yunsung Kim, Jihan Chrzan, Daryl Walsh, Aron Blau, Samuel M. Asta, Mark Krishnapriyan, Aditi S. Chemical Physics Materials Science Computational Engineering, Finance, and Science Machine learning interatomic potentials (MLIPs) have revolutionized molecular and materials modeling, but existing benchmarks suffer from data leakage, limited transferability, and an over-reliance on error-based metrics tied to specific density functional theory (DFT) references. We introduce MLIP Arena, a benchmark platform that evaluates force field performance based on physics awareness, chemical reactivity, stability under extreme conditions, and predictive capabilities for thermodynamic properties and physical phenomena. By moving beyond static DFT references and revealing the important failure modes of current foundation MLIPs in real-world settings, MLIP Arena provides a reproducible framework to guide the next-generation MLIP development toward improved predictive accuracy and runtime efficiency while maintaining physical consistency. The Python package and online leaderboard are available at https://github.com/atomind-ai/mlip-arena. |
| title | MLIP Arena: Advancing Fairness and Transparency in Machine Learning Interatomic Potentials via an Open, Accessible Benchmark Platform |
| topic | Chemical Physics Materials Science Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2509.20630 |