Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts
Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed training distribution. This makes it difficult to determine whether a model has learned generalizable physical dynamics or only performs well under particular settings. We construct a benchmark with 8 physical dynamics, 3 training-data mixtures, and 25 test regimes induced by dynamic-scale and initial-condition complexity shifts, covering in-distribution, distribution-shift, and out-of-distribution settings. We evaluate five physics foundation model architectures and four model variants per architecture (scratch and t...
| Authors | Mengdi Chu, Yang Liu, Ayan Biswas et al. |
|---|---|
| Primary category | cs.LG |
| Published | 28 May 2026 |
| Last updated at source | 1 July 2026 |
Connected in the knowledge graph
- 90879c/PhysBiasBenchDataset · cited by
Models and datasets referencing this paper
- 90879c/PhysBiasBenchDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.