Same Predictions, Different Harms: Causal Auditing of Patient World Models

Excerpt

arXiv:2610.05198v1 Announce Type: cross Abstract: Patient world models used for clinical trial simulation can agree on transition kernels and arm-specific risks, yet disagree on the fraction of patients harmed by switching treatment---the counterfactual quantity that matters for intervention-aware reasoning. We audit this reliability gap in a two-stage shared-response SCM: a categorical intermediate health state is followed by common terminal care. Under independent stages, the sharp harm interv