Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics

Excerpt

arXiv:2610.00280v1 Announce Type: new Abstract: A world model learns to forecast how a physical system evolves from recorded trajectories, yet the systems it imitates obey physical laws that are neither fully supplied nor reliably respected. The model may create energy, drift or diverge over long rollouts, and answer a changed law query using the law observed during training. We ask how much general physical structure must be hard coded into a world model, and how much system-specific physics ca