Most PDE foundation models are pretrained and fine-tuned on fluid-centric benchmarks. Their utility under extreme-loading material dynamics remains unclear. We benchmark out-of-distribution transfer on two discontinuity-dominated regimes in which shocks, evolving interfaces, and fracture produce highly non-smooth fields: shock-driven multi-material interface dynamics (perturbed layered interface or PLI) and dynamic fracture/failure evolution (FRAC). We formulate the downstream task as terminal-state prediction, i.e., learning a long-horizon map that predicts the final state directly from the first snapshot without intermediate supervision. Using a unified training and evaluation protocol, we evaluate two open-source pretrained PDE foundation models, POSEIDON and MORPH, and compare fine-tuning from pretrained weights against training from scratch across training-set sizes to quantify sample efficiency under distribution shift.
@article{arxiv.2603.04354,
title = {Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading},
author = {Mahindra Rautela and Alexander Most and Siddharth Mansingh and Aleksandra Pachalieva and Bradley Love and Daniel O Malley and Alexander Scheinker and Kyle Hickmann and Diane Oyen and Nathan Debardeleben and Earl Lawrence and Ayan Biswas},
journal= {arXiv preprint arXiv:2603.04354},
year = {2026}
}