{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BBI7DRTNGWVI2SSOPVCZCD523C","short_pith_number":"pith:BBI7DRTN","schema_version":"1.0","canonical_sha256":"0851f1c66d35aa8d4a4e7d45910fbad8baf5858a7ffa53b0826fa45d9a9782d5","source":{"kind":"arxiv","id":"2504.16693","version":2},"attestation_state":"computed","paper":{"title":"PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Hang Zhao, Kai Xu, Qin Zou, Ruizhen Hu, Wenxuan Li, Yu Du, Zhiyuan Yu","submitted_at":"2025-04-23T13:27:07Z","abstract_excerpt":"While non-prehensile manipulation (e.g., controlled pushing/poking) constitutes a foundational robotic skill, its learning remains challenging due to the high sensitivity to complex physical interactions involving friction and restitution. To achieve robust policy learning and generalization, we opt to learn a world model of the 3D rigid body dynamics involved in non-prehensile manipulations and use it for model-based reinforcement learning. We propose PIN-WM, a Physics-INformed World Model that enables efficient end-to-end identification of a 3D rigid body dynamical system from visual observa"},"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":"2504.16693","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-23T13:27:07Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"27c7929b34a84eabd4bf95870698aec96f10fb31f2602af3d40c1c45a8244612","abstract_canon_sha256":"1a1bb577075f262cfc54d2025947ab14483e32cce4666b98953c39234b6894ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:57.031836Z","signature_b64":"holV5iJGYmQQZbm4/nJ4my5DiyaIdaXiI3oWJMYjOISXkkyehpPIkhhNhQgbwwYC4y2LP67xfqsqRZNsntf1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0851f1c66d35aa8d4a4e7d45910fbad8baf5858a7ffa53b0826fa45d9a9782d5","last_reissued_at":"2026-07-05T10:57:57.031329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:57.031329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Hang Zhao, Kai Xu, Qin Zou, Ruizhen Hu, Wenxuan Li, Yu Du, Zhiyuan Yu","submitted_at":"2025-04-23T13:27:07Z","abstract_excerpt":"While non-prehensile manipulation (e.g., controlled pushing/poking) constitutes a foundational robotic skill, its learning remains challenging due to the high sensitivity to complex physical interactions involving friction and restitution. To achieve robust policy learning and generalization, we opt to learn a world model of the 3D rigid body dynamics involved in non-prehensile manipulations and use it for model-based reinforcement learning. We propose PIN-WM, a Physics-INformed World Model that enables efficient end-to-end identification of a 3D rigid body dynamical system from visual observa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16693","kind":"arxiv","version":2},"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/2504.16693/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":"2504.16693","created_at":"2026-07-05T10:57:57.031390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16693v2","created_at":"2026-07-05T10:57:57.031390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16693","created_at":"2026-07-05T10:57:57.031390+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBI7DRTNGWVI","created_at":"2026-07-05T10:57:57.031390+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBI7DRTNGWVI2SSO","created_at":"2026-07-05T10:57:57.031390+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBI7DRTN","created_at":"2026-07-05T10:57:57.031390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":224,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01938","citing_title":"PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01950","citing_title":"Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18208","citing_title":"Looped World Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16395","citing_title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17580","citing_title":"ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":224,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C","json":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C.json","graph_json":"https://pith.science/api/pith-number/BBI7DRTNGWVI2SSOPVCZCD523C/graph.json","events_json":"https://pith.science/api/pith-number/BBI7DRTNGWVI2SSOPVCZCD523C/events.json","paper":"https://pith.science/paper/BBI7DRTN"},"agent_actions":{"view_html":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C","download_json":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C.json","view_paper":"https://pith.science/paper/BBI7DRTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16693&json=true","fetch_graph":"https://pith.science/api/pith-number/BBI7DRTNGWVI2SSOPVCZCD523C/graph.json","fetch_events":"https://pith.science/api/pith-number/BBI7DRTNGWVI2SSOPVCZCD523C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C/action/storage_attestation","attest_author":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C/action/author_attestation","sign_citation":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C/action/citation_signature","submit_replication":"https://pith.science/pith/BBI7DRTNGWVI2SSOPVCZCD523C/action/replication_record"}},"created_at":"2026-07-05T10:57:57.031390+00:00","updated_at":"2026-07-05T10:57:57.031390+00:00"}