# Event-Conditioned Diagnostics of Kinematic, Contact, and Object-Permanence Structure in Passive Object-State World Models

arXiv: https://arxiv.org/abs/2606.28455 · HTML: https://mlsanity.com/paper/2606.28455/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 21 of its 21 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 21 of 21)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Physion: Evaluating Physical Prediction from Vision in Humans and Machines](https://mlsanity.com/paper/2106.08261/) (2021)
- [SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models](https://mlsanity.com/paper/2210.05861/) (2022)
- [PHYRE: A New Benchmark for Physical Reasoning](https://mlsanity.com/paper/1908.05656/) (2019)
- [CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning](https://mlsanity.com/paper/1910.04744/) (2019)
- [IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments](https://mlsanity.com/paper/2506.09849/) (2025)
- [Learning Object Permanence from Video](https://mlsanity.com/paper/2003.10469/) (2020)
- [Interpreting Physics in Video World Models](https://mlsanity.com/paper/2602.07050/) (2026)
- [Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions](https://mlsanity.com/paper/2302.11850/) (2023)
- [Variational Causal Dynamics: Discovering Modular World Models from Interventions](https://mlsanity.com/paper/2206.11131/) (2022)
- [Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization](https://mlsanity.com/paper/2508.20294/) (2025)
- [What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators](https://mlsanity.com/paper/2603.21546/) (2026)
- [Learning Object Permanence from Videos via Latent Imaginations](https://mlsanity.com/paper/2310.10372/) (2023)
- [Causal Physics Steering in Video World Models via Concept Activation Vectors](https://mlsanity.com/paper/2605.24322/) (2026)
- [OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematics](https://mlsanity.com/paper/2404.18423/) (2024)
- [CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics](https://mlsanity.com/paper/2604.07712/) (2026)

## Abstract (arXiv)

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 separates three questions: whether event-regime information is readable, whether event context changes the relative emphasis of kinematic-, contact-, and object-permanence-related readouts, and whether suppressing readout-aligned directions affects prediction. Using a balanced controlled-generator dataset with free-motion, collision, and occlusion events, we evaluate GRU, Transformer-lite, and RSSM-lite transition models under a fixed-horizon forecasting setup. Across three independent seeds, all three architectures learn useful predictive dynamics and support reliable event-regime readout. Event context systematically shifts the relative readout pattern: free motion is kinematic-dominant, collision increases contact-related structure, and occlusion increases object-permanence-related structure. Time-aligned analyses show corresponding phase-related shifts. Fixed-horizon projection Causal Field Effect (CFE), used here as a functional-sensitivity test, gives the clearest evidence for contact-aligned structure in collision-contact windows. Object-permanence-aligned structure is also sensitive during hard occlusion, but control specificity remains mixed. These results support event-conditioned latent structure and functional sensitivity without implying explicit physical modules or isolated causal circuits.