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

[2606.28455] Event-Conditioned Diagnostics of Kinematic, Contact, and Object-Permanence Structure in Passive Object-State World Models Skip to main content Search Submit Donate Log in Computer Science > Robotics arXiv:2606.28455 (cs) [Submitted on 26 Jun 2026 ( v1 ), last revised 22 Aug 2026 (this version, v3)] Title: Event-Conditioned Diagnostics of Kinematic, Contact, and Object-Permanence Structure in Passive Object-State World Models Authors: Yang Liu , Yuming Chen View PDF Abstract: 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. Comments: Revised version: updated the title and terminology to use a more conservative latent-structure framing, added a third independent training seed across the evaluated model architectures, and regenerated the corresponding analyses, figures, and numerical results. The public reproducibility repository has also been updated. The main conclusions remain unchanged Subjects: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) ACM classes: I.2.m Cite as: arXiv:2606.28455 [cs.RO] (or arXiv:2606.28455v3 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2606.28455 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yang Liu [ view email ] [v1] Fri, 26 Jun 2026 10:11:59 UTC (982 KB) [v2] Fri, 14 Aug 2026 01:38:03 UTC (971 KB) [v3] Sat, 22 Aug 2026 00:00:48 UTC (1,023 KB) Full-text links: Access Paper: View PDF view license Additional Features Audio Summary Current browse context: cs.RO < prev | next > new | recent | 2026-06 Change to browse by: cs cs.AI cs.LG References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Event-Conditioned Diagnostics of Kinematic, Contact, and Object-Permanence Structure in Passive Object-State World Models#665831
• From chopped to cooked: Design and inference in physical environments#168445
• BadWAM: When World-Action Models Dream Right but Act Wrong#1049924
• WALL-WM: Carving World Action Modeling at the Event Joints#973196
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models#441846