# PET-MAD, a lightweight universal interatomic potential for advanced materials modeling

arXiv: https://arxiv.org/abs/2503.14118 · HTML: https://mlsanity.com/paper/2503.14118/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 85 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 16 of 16)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024)
- [The Open Catalyst 2020 (OC20) Dataset and Community Challenges](https://mlsanity.com/paper/2010.09990/) (2020)
- [Machine Learning Force Fields](https://mlsanity.com/paper/2010.07067/) (2020)
- [SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials](https://mlsanity.com/paper/2209.10702/) (2022)
- [Machine Learning of coarse-grained Molecular Dynamics Force Fields](https://mlsanity.com/paper/1812.01736/) (2018)
- [Orb: A Fast, Scalable Neural Network Potential](https://mlsanity.com/paper/2410.22570/) (2024)
- [Smooth, exact rotational symmetrization for deep learning on point clouds](https://mlsanity.com/paper/2305.19302/) (2023)
- [Matbench Discovery -- A framework to evaluate machine learning crystal stability predictions](https://mlsanity.com/paper/2308.14920/) (2023)
- [The dark side of the forces: assessing non-conservative force models for atomistic machine learning](https://mlsanity.com/paper/2412.11569/) (2024)
- [AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance](https://mlsanity.com/paper/2003.12476/) (2020)
- [Probing the effects of broken symmetries in machine learning](https://mlsanity.com/paper/2406.17747/) (2024)
- [A prediction rigidity formalism for low-cost uncertainties in trained neural networks](https://mlsanity.com/paper/2403.02251/) (2024)
- [A data-driven interpretation of the stability of molecular crystals](https://mlsanity.com/paper/2209.10709/) (2022)
- [Grappa -- A Machine Learned Molecular Mechanics Force Field](https://mlsanity.com/paper/2404.00050/) (2024)

## Built on by (most cited first, 23 of 23)

- [Universally Converging Representations of Matter Across Scientific Foundation Models](https://mlsanity.com/paper/2512.03750/) (2025)
- [Pushing the limits of unconstrained machine-learned interatomic potentials](https://mlsanity.com/paper/2601.16195/) (2026)
- [MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistry](https://mlsanity.com/paper/2602.19411/) (2026)
- [A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention](https://mlsanity.com/paper/2603.06567/) (2026)
- [Transformers Discover Molecular Structure Without Graph Priors](https://mlsanity.com/paper/2510.02259/) (2025)
- [Representing spherical tensors with scalar-based machine-learning models](https://mlsanity.com/paper/2505.05404/) (2025)
- [Two-dimensional RMSD projections for reaction path visualization and validation](https://mlsanity.com/paper/2512.07329/) (2025)
- [Global Plane Waves From Local Gaussians: Periodic Charge Densities in a Blink](https://mlsanity.com/paper/2601.19966/) (2026)
- [CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models](https://mlsanity.com/paper/2605.08960/) (2026)
- [Reciprocal Space Attention for Learning Long-Range Interactions](https://mlsanity.com/paper/2510.13055/) (2025)
- [From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures](https://mlsanity.com/paper/2602.04861/) (2026)
- [How unconstrained machine-learning models learn physical symmetries](https://mlsanity.com/paper/2603.24638/) (2026)
- [Enhanced Climbing Image Nudged Elastic Band method with Hessian Eigenmode Alignment](https://mlsanity.com/paper/2601.12630/) (2026)
- [Broken neural scaling laws in materials science](https://mlsanity.com/paper/2602.05702/) (2026)
- [Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning](https://mlsanity.com/paper/2605.08885/) (2026)
- [Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials](https://mlsanity.com/paper/2605.08988/) (2026)
- [MALOQ: Massively Accelerated Learning of Operators for Quantum Transport](https://mlsanity.com/paper/2606.28911/) (2026)
- [EquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation](https://mlsanity.com/paper/2607.05559/) (2026)
- [Reaction-network reasoning with frontier models for experimentally confirmed catalyst-selectivity hypotheses](https://mlsanity.com/paper/2607.08003/) (2026)
- [Active rejection enables reliable generalization of universal machine-learning interatomic potentials](https://mlsanity.com/paper/2607.09456/) (2026)
- [Universal Thermodynamic Interatomic Potentials for Crystalline Materials](https://mlsanity.com/paper/2608.14502/) (2026)
- [Truncated automatic sparse differentiation for machine learning interatomic potentials](https://mlsanity.com/paper/2609.20510/) (2026)
- [SoLiD26: A First Principles Solid-Liquid Interface Dataset for Machine-learned Interatomic Potentials](https://mlsanity.com/paper/2609.28013/) (2026)

## Abstract (arXiv)

Machine-learning interatomic potentials (MLIPs) have greatly extended the reach of atomic-scale simulations, offering the accuracy of first-principles calculations at a fraction of the cost. Leveraging large quantum mechanical databases and expressive architectures, recent ''universal'' models deliver qualitative accuracy across the periodic table but are often biased toward low-energy configurations. We introduce PET-MAD, a generally applicable MLIP trained on a dataset combining stable inorganic and organic solids, systematically modified to enhance atomic diversity. Using a moderate but highly-consistent level of electronic-structure theory, we assess PET-MAD's accuracy on established benchmarks and advanced simulations of six materials. Despite the small training set and lightweight architecture, PET-MAD is competitive with state-of-the-art MLIPs for inorganic solids, while also being reliable for molecules, organic materials, and surfaces. It is stable and fast, enabling the near-quantitative study of thermal and quantum mechanical fluctuations, functional properties, and phase transitions out of the box. It can be efficiently fine-tuned to deliver full quantum mechanical accuracy with a minimal number of targeted calculations.