{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2OCULL7GRGZQ4GTRBJET657KNN","short_pith_number":"pith:2OCULL7G","schema_version":"1.0","canonical_sha256":"d38545afe689b30e1a710a493f77ea6b5ffd8a81f0300779dbf97a06cded49c3","source":{"kind":"arxiv","id":"2606.01950","version":1},"attestation_state":"computed","paper":{"title":"Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jens U. Kreber, Joerg Stueckler, Lukas Mack","submitted_at":"2026-06-01T09:12:07Z","abstract_excerpt":"World models enable intelligent agents to predict the consequences of their actions on the environment. In this paper, we propose Multi Rigid Object Gaussian World Model (MRO-GWM), a novel model that learns action-conditional dynamics of rigid objects in 3D. By representing the scene by object-centric Gaussians, we can represent arbitrary object shapes and multi-object scenes. We develop a novel spatio-temporal transformer architecture that predicts future rigid body motion from a history of object Gaussians and future actions. Objects are represented by their Gaussians in a canonical frame, w"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.01950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T09:12:07Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"369a9554382db3b659a0a05939fb18bdb58d79fdbb5a1ddd17cdac5ee9ac0822","abstract_canon_sha256":"e39e5d38f15e1f4290716f9752e752c96cec9ed8e0ed38571c978705b7bec593"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:01.392486Z","signature_b64":"mXpIzV7sL3f688KwU+zCC/+448/hLzvexGiZxbhOq7NyMrhb3vTgZ/WBREPdazrshjCKdbhknRx/AHNotyhZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d38545afe689b30e1a710a493f77ea6b5ffd8a81f0300779dbf97a06cded49c3","last_reissued_at":"2026-06-02T02:05:01.392070Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:01.392070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jens U. Kreber, Joerg Stueckler, Lukas Mack","submitted_at":"2026-06-01T09:12:07Z","abstract_excerpt":"World models enable intelligent agents to predict the consequences of their actions on the environment. In this paper, we propose Multi Rigid Object Gaussian World Model (MRO-GWM), a novel model that learns action-conditional dynamics of rigid objects in 3D. By representing the scene by object-centric Gaussians, we can represent arbitrary object shapes and multi-object scenes. We develop a novel spatio-temporal transformer architecture that predicts future rigid body motion from a history of object Gaussians and future actions. Objects are represented by their Gaussians in a canonical frame, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01950","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.01950/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.01950","created_at":"2026-06-02T02:05:01.392139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01950v1","created_at":"2026-06-02T02:05:01.392139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01950","created_at":"2026-06-02T02:05:01.392139+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OCULL7GRGZQ","created_at":"2026-06-02T02:05:01.392139+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OCULL7GRGZQ4GTR","created_at":"2026-06-02T02:05:01.392139+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OCULL7G","created_at":"2026-06-02T02:05:01.392139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN","json":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN.json","graph_json":"https://pith.science/api/pith-number/2OCULL7GRGZQ4GTRBJET657KNN/graph.json","events_json":"https://pith.science/api/pith-number/2OCULL7GRGZQ4GTRBJET657KNN/events.json","paper":"https://pith.science/paper/2OCULL7G"},"agent_actions":{"view_html":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN","download_json":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN.json","view_paper":"https://pith.science/paper/2OCULL7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01950&json=true","fetch_graph":"https://pith.science/api/pith-number/2OCULL7GRGZQ4GTRBJET657KNN/graph.json","fetch_events":"https://pith.science/api/pith-number/2OCULL7GRGZQ4GTRBJET657KNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN/action/storage_attestation","attest_author":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN/action/author_attestation","sign_citation":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN/action/citation_signature","submit_replication":"https://pith.science/pith/2OCULL7GRGZQ4GTRBJET657KNN/action/replication_record"}},"created_at":"2026-06-02T02:05:01.392139+00:00","updated_at":"2026-06-02T02:05:01.392139+00:00"}