Event-Conditioned Diagnostics of Kinematic, Contact, and Object-Permanence Fields in Passive Object-State World Models
For researchers studying latent representations in world models, this work provides a method to probe how physical knowledge is structured and used, though the findings are incremental as they confirm expected event-conditioned organization without demonstrating novel causal mechanisms.
The paper introduces a diagnostic protocol to study how passive object-state world models organize physical information (kinematic, contact, object-permanence) in their latent dynamics, conditioned on events (free motion, collision, occlusion). Results show that event contexts systematically reweight latent field readouts and that suppressing field-aligned directions degrades event-relevant prediction, with strongest evidence for contact-aligned structure in collision events.
World models can predict future physical states, but prediction accuracy alone does not explain how physical information is organized and used inside their latent dynamics. We introduce a controlled diagnostic protocol for studying event-conditioned latent physical structure in passive object-state world models. The protocol tests whether hidden representations encode event-regime information, whether event contexts reweight non-exclusive physical field readouts, and whether field-aligned representational components have functional consequences for prediction. Using a balanced controlled-generator dataset with free-motion, collision, and occlusion events, we evaluate recurrent, attention-based, and latent state-space transition models under a fixed-horizon forecasting setup. The models learn useful predictive dynamics and their hidden states support reliable event-regime readout. Event contexts systematically reweight kinematic, contact, and object-permanence field readouts: free motion is kinematic-dominant, collision combines kinematic and contact structure, and occlusion combines motion-related and object-permanence structure. Time-aligned and directional-consistency analyses further show phase-related shifts in field emphasis. Finally, fixed-horizon projection causal field effect (CFE) shows that suppressing field-aligned directions can degrade event-relevant prediction, with strongest evidence for contact-aligned structure in collision-contact windows and more qualified evidence for object-permanence-aligned structure in hard-occlusion hidden windows. These results support event-conditioned organization and fixed-horizon functional sensitivity of latent physical fields, while not implying explicit physical modules, isolated causal circuits, or context-invariant sliding-window generalization.