{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GPGORVZ7T5FXQJTMGT52SOFDUW","short_pith_number":"pith:GPGORVZ7","schema_version":"1.0","canonical_sha256":"33cce8d73f9f4b78266c34fba938a3a5b087b7d5fb92ef36ba344545fee59df1","source":{"kind":"arxiv","id":"2405.16645","version":1},"attestation_state":"computed","paper":{"title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Hanwen Liang, Hanxue Liang, Konstantinos N. Plataniotis, Yao Zhao, Yunchao Wei, Yuyang Yin, Zhangyang Wang","submitted_at":"2024-05-26T17:47:34Z","abstract_excerpt":"The availability of large-scale multimodal datasets and advancements in diffusion models have significantly accelerated progress in 4D content generation. Most prior approaches rely on multiple image or video diffusion models, utilizing score distillation sampling for optimization or generating pseudo novel views for direct supervision. However, these methods are hindered by slow optimization speeds and multi-view inconsistency issues. Spatial and temporal consistency in 4D geometry has been extensively explored respectively in 3D-aware diffusion models and traditional monocular video diffusio"},"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":"2405.16645","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-26T17:47:34Z","cross_cats_sorted":[],"title_canon_sha256":"4b1271a76565c1d8590e0d5dd51ada7201a44d9a3117f3eda50155fce352fa5c","abstract_canon_sha256":"1571809964e8c899608565deccd14832a9629b8607ea03eb0c754971d7e6c954"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:33.555508Z","signature_b64":"vJimx1mS9KIVt1pUa8q04a9TJ6f4cPmOovtO/EmQc+HSa4hG+5jlPu5DpJ5juOzHg/jD/qbN+pu85kVGu/4LCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33cce8d73f9f4b78266c34fba938a3a5b087b7d5fb92ef36ba344545fee59df1","last_reissued_at":"2026-07-05T08:23:33.555062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:33.555062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Hanwen Liang, Hanxue Liang, Konstantinos N. Plataniotis, Yao Zhao, Yunchao Wei, Yuyang Yin, Zhangyang Wang","submitted_at":"2024-05-26T17:47:34Z","abstract_excerpt":"The availability of large-scale multimodal datasets and advancements in diffusion models have significantly accelerated progress in 4D content generation. Most prior approaches rely on multiple image or video diffusion models, utilizing score distillation sampling for optimization or generating pseudo novel views for direct supervision. However, these methods are hindered by slow optimization speeds and multi-view inconsistency issues. Spatial and temporal consistency in 4D geometry has been extensively explored respectively in 3D-aware diffusion models and traditional monocular video diffusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16645","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/2405.16645/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":"2405.16645","created_at":"2026-07-05T08:23:33.555118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16645v1","created_at":"2026-07-05T08:23:33.555118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16645","created_at":"2026-07-05T08:23:33.555118+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPGORVZ7T5FX","created_at":"2026-07-05T08:23:33.555118+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPGORVZ7T5FXQJTM","created_at":"2026-07-05T08:23:33.555118+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPGORVZ7","created_at":"2026-07-05T08:23:33.555118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08246","citing_title":"SkelGen4D: Weakly-Supervised Skeleton-Based 4D Generation for Text-Driven Mesh Animation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10988","citing_title":"AnimaSpark: A Feed-Forward Method for Animating Arbitrary 3D Objects","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09187","citing_title":"CP4D: Compositional Physics-aware 4D Scene Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09176","citing_title":"LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19786","citing_title":"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26917","citing_title":"AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22700","citing_title":"Generative Modeling of Neurodegenerative Brain Anatomy with 4D Longitudinal Diffusion Model","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04527","citing_title":"Velox: Learning Representations of 4D Geometry and Appearance","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW","json":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW.json","graph_json":"https://pith.science/api/pith-number/GPGORVZ7T5FXQJTMGT52SOFDUW/graph.json","events_json":"https://pith.science/api/pith-number/GPGORVZ7T5FXQJTMGT52SOFDUW/events.json","paper":"https://pith.science/paper/GPGORVZ7"},"agent_actions":{"view_html":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW","download_json":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW.json","view_paper":"https://pith.science/paper/GPGORVZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16645&json=true","fetch_graph":"https://pith.science/api/pith-number/GPGORVZ7T5FXQJTMGT52SOFDUW/graph.json","fetch_events":"https://pith.science/api/pith-number/GPGORVZ7T5FXQJTMGT52SOFDUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW/action/storage_attestation","attest_author":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW/action/author_attestation","sign_citation":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW/action/citation_signature","submit_replication":"https://pith.science/pith/GPGORVZ7T5FXQJTMGT52SOFDUW/action/replication_record"}},"created_at":"2026-07-05T08:23:33.555118+00:00","updated_at":"2026-07-05T08:23:33.555118+00:00"}