{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MO3QYE7ID3GIBAZX3KJSFG4KRI","short_pith_number":"pith:MO3QYE7I","schema_version":"1.0","canonical_sha256":"63b70c13e81ecc808337da93229b8a8a2157fe31a8e07051bc0266d44d2a5a90","source":{"kind":"arxiv","id":"2605.22882","version":1},"attestation_state":"computed","paper":{"title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ao Qu, Fangneng Zhan, Grace Chen, Hang Hua, Kaichen Zhou, Mengyu Wang, Paul Pu Liang, Xinhai Chang, Yilun Du, Yuzhen Chen, Zhuang Liu","submitted_at":"2026-05-20T21:36:44Z","abstract_excerpt":"Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time. As a result, the generated videos appear plausible, yet lack the physical grounding required for reliable action execution, such as robot manipulation. We present GEM-4D, a geometry-grounded video world model that resolves this limitation by injecting dense 4D correspondence supervision, distilled from a pretrained geometry foundation model, into the video generative backbone during training. This supervision enables the model to jointly capture "},"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":"2605.22882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:36:44Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5ef0b439a9a8f42b26304de4a8afa8a71ab3fb889e639586151342caa87a49c4","abstract_canon_sha256":"dfd29fe6a869ce5278680f446aebc1a0b5661308e06241cf77e098c496918291"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:28.521483Z","signature_b64":"min91L7VTnqs/CHYZP3AdIKFYyefo7E3lO+yFRXBPYktHPKYgFfU6hrEvEevz+FyFtsjFAeDSiDhfyGlUkI3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b70c13e81ecc808337da93229b8a8a2157fe31a8e07051bc0266d44d2a5a90","last_reissued_at":"2026-05-25T02:01:28.520990Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:28.520990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Ao Qu, Fangneng Zhan, Grace Chen, Hang Hua, Kaichen Zhou, Mengyu Wang, Paul Pu Liang, Xinhai Chang, Yilun Du, Yuzhen Chen, Zhuang Liu","submitted_at":"2026-05-20T21:36:44Z","abstract_excerpt":"Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time. As a result, the generated videos appear plausible, yet lack the physical grounding required for reliable action execution, such as robot manipulation. We present GEM-4D, a geometry-grounded video world model that resolves this limitation by injecting dense 4D correspondence supervision, distilled from a pretrained geometry foundation model, into the video generative backbone during training. This supervision enables the model to jointly capture "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22882","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/2605.22882/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":"2605.22882","created_at":"2026-05-25T02:01:28.521058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22882v1","created_at":"2026-05-25T02:01:28.521058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22882","created_at":"2026-05-25T02:01:28.521058+00:00"},{"alias_kind":"pith_short_12","alias_value":"MO3QYE7ID3GI","created_at":"2026-05-25T02:01:28.521058+00:00"},{"alias_kind":"pith_short_16","alias_value":"MO3QYE7ID3GIBAZX","created_at":"2026-05-25T02:01:28.521058+00:00"},{"alias_kind":"pith_short_8","alias_value":"MO3QYE7I","created_at":"2026-05-25T02:01:28.521058+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/MO3QYE7ID3GIBAZX3KJSFG4KRI","json":"https://pith.science/pith/MO3QYE7ID3GIBAZX3KJSFG4KRI.json","graph_json":"https://pith.science/api/pith-number/MO3QYE7ID3GIBAZX3KJSFG4KRI/graph.json","events_json":"https://pith.science/api/pith-number/MO3QYE7ID3GIBAZX3KJSFG4KRI/events.json","paper":"https://pith.science/paper/MO3QYE7I"},"agent_actions":{"view_html":"https://pith.science/pith/MO3QYE7ID3GIBAZX3KJSFG4KRI","download_json":"https://pith.science/pith/MO3QYE7ID3GIBAZX3KJSFG4KRI.json","view_paper":"https://pith.science/paper/MO3QYE7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22882&json=true","fetch_graph":"https://pith.science/api/pith-number/MO3QYE7ID3GIBAZX3KJSFG4KRI/graph.json","fetch_events":"https://pith.science/api/pith-number/MO3QYE7ID3GIBAZX3KJSFG4KRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MO3QYE7ID3GIBAZX3KJSFG4KRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MO3QYE7ID3GIBAZX3KJSFG4KRI/action/storage_attestation","attest_author":"https://pith.science/pith/MO3QYE7ID3GIBAZX3KJSFG4KRI/action/author_attestation","sign_citation":"https://pith.science/pith/MO3QYE7ID3GIBAZX3KJSFG4KRI/action/citation_signature","submit_replication":"https://pith.science/pith/MO3QYE7ID3GIBAZX3KJSFG4KRI/action/replication_record"}},"created_at":"2026-05-25T02:01:28.521058+00:00","updated_at":"2026-05-25T02:01:28.521058+00:00"}