{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QCADFRMXRXEWY5QGO4YSJQTOWZ","short_pith_number":"pith:QCADFRMX","schema_version":"1.0","canonical_sha256":"808032c5978dc96c7606773124c26eb67be207ca04714bd1a630e5ec08ac35c4","source":{"kind":"arxiv","id":"2405.03150","version":2},"attestation_state":"computed","paper":{"title":"Video Diffusion Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Melnik, Cong Lu, Helge Ritter, Michal Ljubljanac, Qi Yan, Weiming Ren","submitted_at":"2024-05-06T04:01:42Z","abstract_excerpt":"Diffusion generative models have recently become a powerful technique for creating and modifying high-quality, coherent video content. This survey provides a comprehensive overview of the critical components of diffusion models for video generation, including their applications, architectural design, and temporal dynamics modeling. The paper begins by discussing the core principles and mathematical formulations, then explores various architectural choices and methods for maintaining temporal consistency. A taxonomy of applications is presented, categorizing models based on input modalities suc"},"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":"2405.03150","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T04:01:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"421d75e10e375d7ca32b645a9d8d532d55fdcfc9c5d4cc5a341dc20230722693","abstract_canon_sha256":"65feaf6a5cddca28378bb9c3546f0469d31ceed24dff19d9085370a40dd87be9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:11.315112Z","signature_b64":"wTqrRa0CcnguAEnb51DKPstWPzR7qV+EJSSVOVeVN8OpuqU6khquYGnAmcltEYBMROVKBP5D6LSCW7e+I2jmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"808032c5978dc96c7606773124c26eb67be207ca04714bd1a630e5ec08ac35c4","last_reissued_at":"2026-07-05T09:36:11.314590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:11.314590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Diffusion Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Melnik, Cong Lu, Helge Ritter, Michal Ljubljanac, Qi Yan, Weiming Ren","submitted_at":"2024-05-06T04:01:42Z","abstract_excerpt":"Diffusion generative models have recently become a powerful technique for creating and modifying high-quality, coherent video content. This survey provides a comprehensive overview of the critical components of diffusion models for video generation, including their applications, architectural design, and temporal dynamics modeling. The paper begins by discussing the core principles and mathematical formulations, then explores various architectural choices and methods for maintaining temporal consistency. A taxonomy of applications is presented, categorizing models based on input modalities suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03150","kind":"arxiv","version":2},"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/2405.03150/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":"2405.03150","created_at":"2026-07-05T09:36:11.314656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03150v2","created_at":"2026-07-05T09:36:11.314656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03150","created_at":"2026-07-05T09:36:11.314656+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCADFRMXRXEW","created_at":"2026-07-05T09:36:11.314656+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCADFRMXRXEWY5QG","created_at":"2026-07-05T09:36:11.314656+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCADFRMX","created_at":"2026-07-05T09:36:11.314656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19271","citing_title":"TurboServe: Serving Streaming Video Generation Efficiently and Economically","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20707","citing_title":"GEOPHYS: The Geometry of Physical Plausibility","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03201","citing_title":"Reinforcement Learning from Cross-domain Videos with Video Prediction Model","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13419","citing_title":"Diffusion Models Memorize in Training -- and Generalize in Inference","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17812","citing_title":"ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11367","citing_title":"3D-Belief: Embodied Belief Inference via Generative 3D World Modeling","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25289","citing_title":"Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ","json":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ.json","graph_json":"https://pith.science/api/pith-number/QCADFRMXRXEWY5QGO4YSJQTOWZ/graph.json","events_json":"https://pith.science/api/pith-number/QCADFRMXRXEWY5QGO4YSJQTOWZ/events.json","paper":"https://pith.science/paper/QCADFRMX"},"agent_actions":{"view_html":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ","download_json":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ.json","view_paper":"https://pith.science/paper/QCADFRMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03150&json=true","fetch_graph":"https://pith.science/api/pith-number/QCADFRMXRXEWY5QGO4YSJQTOWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QCADFRMXRXEWY5QGO4YSJQTOWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ/action/storage_attestation","attest_author":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ/action/author_attestation","sign_citation":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ/action/citation_signature","submit_replication":"https://pith.science/pith/QCADFRMXRXEWY5QGO4YSJQTOWZ/action/replication_record"}},"created_at":"2026-07-05T09:36:11.314656+00:00","updated_at":"2026-07-05T09:36:11.314656+00:00"}