{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MO3QYE7ID3GIBAZX3KJSFG4KRI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dfd29fe6a869ce5278680f446aebc1a0b5661308e06241cf77e098c496918291","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:36:44Z","title_canon_sha256":"5ef0b439a9a8f42b26304de4a8afa8a71ab3fb889e639586151342caa87a49c4"},"schema_version":"1.0","source":{"id":"2605.22882","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22882","created_at":"2026-05-25T02:01:28Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22882v1","created_at":"2026-05-25T02:01:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22882","created_at":"2026-05-25T02:01:28Z"},{"alias_kind":"pith_short_12","alias_value":"MO3QYE7ID3GI","created_at":"2026-05-25T02:01:28Z"},{"alias_kind":"pith_short_16","alias_value":"MO3QYE7ID3GIBAZX","created_at":"2026-05-25T02:01:28Z"},{"alias_kind":"pith_short_8","alias_value":"MO3QYE7I","created_at":"2026-05-25T02:01:28Z"}],"graph_snapshots":[{"event_id":"sha256:41b51b81c43291d95b8eeb1d2f73a93c1232903e88046dd17c704e6d4e0bcccc","target":"graph","created_at":"2026-05-25T02:01:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.22882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:36:44Z","title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22882","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b7d77ae044691e5f4cba81f33d12535e58ed5a98b1758f836ae30921369d5c1a","target":"record","created_at":"2026-05-25T02:01:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dfd29fe6a869ce5278680f446aebc1a0b5661308e06241cf77e098c496918291","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T21:36:44Z","title_canon_sha256":"5ef0b439a9a8f42b26304de4a8afa8a71ab3fb889e639586151342caa87a49c4"},"schema_version":"1.0","source":{"id":"2605.22882","kind":"arxiv","version":1}},"canonical_sha256":"63b70c13e81ecc808337da93229b8a8a2157fe31a8e07051bc0266d44d2a5a90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63b70c13e81ecc808337da93229b8a8a2157fe31a8e07051bc0266d44d2a5a90","first_computed_at":"2026-05-25T02:01:28.520990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:28.520990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"min91L7VTnqs/CHYZP3AdIKFYyefo7E3lO+yFRXBPYktHPKYgFfU6hrEvEevz+FyFtsjFAeDSiDhfyGlUkI3Ag==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:28.521483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22882","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7d77ae044691e5f4cba81f33d12535e58ed5a98b1758f836ae30921369d5c1a","sha256:41b51b81c43291d95b8eeb1d2f73a93c1232903e88046dd17c704e6d4e0bcccc"],"state_sha256":"8b549646ee9cd30ca632bbdaac00d1d0439676dae7c95955094a426a8c080072"}