Capture Is Not Propagation: Auditing Action Effects in Latent World Models

A latent world model can encode a task variable while predicting the wrong effect of acting on it. We separate these capabilities with a capture-gated audit: readouts fitted to real data must capture the current query and resolve executed action effects before they are used to score imagined effects, so that propagation failures are not confused with readout failures. Three LeWorldModel checkpoints on Cheetah pass both gates, yet their imagined five-step effects have $R^2$ from $-6.33$ to $-3.36$, well below the zero-effect baseline. The decoded effects are misaligned and amplified even though the complete feature changes align closely with the real ones. Severity varies across Walker, Finger, and other model groups, and the same directional failure appears in independently trained TD-MPC2 runs. On held-out Cheetah action sets, disagreement between model-predicted effects and an environment-fitted reference ranks regret among the candidate actions, so open-loop effect error is visible at the decision level. The same experiments show the limit of any such score: it compares candidate actions with one another, while most of the realized loss comes from the candidate set itself, which no relative score can detect. Evaluating a world model for planning therefore requires testing action effects directly, after capture, and against a no-intervention reference.