# Causal world models under physical parameter shifts: explicit affine coefficients improve extrapolative prediction

- Source: arXiv cs.RO
- Published: 2026-10-22T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/v5gawxy49o6dykg8xa890p3z2
- Original: https://arxiv.org/abs/2610.29088

## Summary

This study examines the degradation of world-model predictions when physical conditions fall outside the training distribution, comparing two causal modeling elements: the inputs available to the predictor and how its mechanism computes their effects. On a synthetic benchmark with shortcut features, a frozen dependency mask derived from paired interventions reduced the out-of-distribution RMSE of a fully connected predictor from 1.769 to 0.697, close to the generator-oracle mask's 0.694.