{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V3YGYH5NEQQ4XTWE3ITAJPTUX3","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":"eeee6e50992c04fb86dcfb6d85195fd11dbefec094c3bb5d1a96ad09d87a5ac7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T17:57:32Z","title_canon_sha256":"6b9fb2a9fabcc54bdf2ae183bb9507d8bf0dfff6b26c5182e13d5f824f6607f8"},"schema_version":"1.0","source":{"id":"2503.21761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21761","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21761v1","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21761","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_12","alias_value":"V3YGYH5NEQQ4","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_16","alias_value":"V3YGYH5NEQQ4XTWE","created_at":"2026-07-05T10:40:30Z"},{"alias_kind":"pith_short_8","alias_value":"V3YGYH5N","created_at":"2026-07-05T10:40:30Z"}],"graph_snapshots":[{"event_id":"sha256:b70bdfd4aab33ba8348feb5d4cd6bcab026e0f473188008940f7232d90f6c287","target":"graph","created_at":"2026-07-05T10:40:30Z","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/2503.21761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising capabilities. However, training a single model for comprehensive 4D understanding remains challenging. We introduce Uni4D, a multi-stage optimization framework that harnesses multiple pretrained models to advance dynamic 3D modeling, including static/dynamic reconstruction, camera pose estimation, and dense 3D motion tracking. Our results show state-of-the-","authors_text":"Albert J. Zhai, David Yifan Yao, Shenlong Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T17:57:32Z","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21761","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:c8b33ce48f33d5a61da27324b34eeb75c1891801b00055cba060e868f329c612","target":"record","created_at":"2026-07-05T10:40:30Z","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":"eeee6e50992c04fb86dcfb6d85195fd11dbefec094c3bb5d1a96ad09d87a5ac7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T17:57:32Z","title_canon_sha256":"6b9fb2a9fabcc54bdf2ae183bb9507d8bf0dfff6b26c5182e13d5f824f6607f8"},"schema_version":"1.0","source":{"id":"2503.21761","kind":"arxiv","version":1}},"canonical_sha256":"aef06c1fad2421cbcec4da2604be74bed757a67222f3bf8bfba8d0ccec25f468","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aef06c1fad2421cbcec4da2604be74bed757a67222f3bf8bfba8d0ccec25f468","first_computed_at":"2026-07-05T10:40:30.247061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:30.247061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fn0NVnqPHIs4Gx5IrOn8TQ4PDaOHmFlH7aoBxGIPXwLf8NZmVnx8xmnTZ1iCm/dsm8ctFpGXiimfObqBCaApAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:30.247520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8b33ce48f33d5a61da27324b34eeb75c1891801b00055cba060e868f329c612","sha256:b70bdfd4aab33ba8348feb5d4cd6bcab026e0f473188008940f7232d90f6c287"],"state_sha256":"f0b855c9ddf91f5d1e12d28b9777a305091425fb9a368c0105008abdce4c4168"}