{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZRNGS3IROK7BO3WATOAWYSK4GW","short_pith_number":"pith:ZRNGS3IR","schema_version":"1.0","canonical_sha256":"cc5a696d1172be176ec09b816c495c359217a76402249a5264ff9ebd9306a0cb","source":{"kind":"arxiv","id":"2507.23785","version":1},"attestation_state":"computed","paper":{"title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Bowen Zhang, Chuxin Wang, Dong Chen, Feng Zhao, Jiaolong Yang, Sicheng Xu","submitted_at":"2025-07-31T17:59:51Z","abstract_excerpt":"In this paper, we present a novel framework for video-to-4D generation that creates high-quality dynamic 3D content from single video inputs. Direct 4D diffusion modeling is extremely challenging due to costly data construction and the high-dimensional nature of jointly representing 3D shape, appearance, and motion. We address these challenges by introducing a Direct 4DMesh-to-GS Variation Field VAE that directly encodes canonical Gaussian Splats (GS) and their temporal variations from 3D animation data without per-instance fitting, and compresses high-dimensional animations into a compact lat"},"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":"2507.23785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T17:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"eacbadd5cc508e81a2a156dda63729b272545ff195a6f2e913c63a677dd409f1","abstract_canon_sha256":"4d603b7d5b71245d2209bb2dd9fa4c2a15ac4b04916d8a15ecdc1b73658303c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:30.909445Z","signature_b64":"buuAPRUxE8tmLmnVDYly6zp6KnBXh92jiA97ekhufA4rZ2Ow6y0ljTNmSLoX4L1WHEmplaCyoH2QOX5owLjKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc5a696d1172be176ec09b816c495c359217a76402249a5264ff9ebd9306a0cb","last_reissued_at":"2026-07-05T11:46:30.908961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:30.908961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Bowen Zhang, Chuxin Wang, Dong Chen, Feng Zhao, Jiaolong Yang, Sicheng Xu","submitted_at":"2025-07-31T17:59:51Z","abstract_excerpt":"In this paper, we present a novel framework for video-to-4D generation that creates high-quality dynamic 3D content from single video inputs. Direct 4D diffusion modeling is extremely challenging due to costly data construction and the high-dimensional nature of jointly representing 3D shape, appearance, and motion. We address these challenges by introducing a Direct 4DMesh-to-GS Variation Field VAE that directly encodes canonical Gaussian Splats (GS) and their temporal variations from 3D animation data without per-instance fitting, and compresses high-dimensional animations into a compact lat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23785","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/2507.23785/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":"2507.23785","created_at":"2026-07-05T11:46:30.909013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23785v1","created_at":"2026-07-05T11:46:30.909013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23785","created_at":"2026-07-05T11:46:30.909013+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRNGS3IROK7B","created_at":"2026-07-05T11:46:30.909013+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRNGS3IROK7BO3WA","created_at":"2026-07-05T11:46:30.909013+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRNGS3IR","created_at":"2026-07-05T11:46:30.909013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13652","citing_title":"World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28215","citing_title":"HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26109","citing_title":"Helix4D: Complex 4D Mesh Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04876","citing_title":"PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19786","citing_title":"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04527","citing_title":"Velox: Learning Representations of 4D Geometry and Appearance","ref_index":117,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW","json":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW.json","graph_json":"https://pith.science/api/pith-number/ZRNGS3IROK7BO3WATOAWYSK4GW/graph.json","events_json":"https://pith.science/api/pith-number/ZRNGS3IROK7BO3WATOAWYSK4GW/events.json","paper":"https://pith.science/paper/ZRNGS3IR"},"agent_actions":{"view_html":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW","download_json":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW.json","view_paper":"https://pith.science/paper/ZRNGS3IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23785&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRNGS3IROK7BO3WATOAWYSK4GW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRNGS3IROK7BO3WATOAWYSK4GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW/action/storage_attestation","attest_author":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW/action/author_attestation","sign_citation":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW/action/citation_signature","submit_replication":"https://pith.science/pith/ZRNGS3IROK7BO3WATOAWYSK4GW/action/replication_record"}},"created_at":"2026-07-05T11:46:30.909013+00:00","updated_at":"2026-07-05T11:46:30.909013+00:00"}