{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UM243XLP3ZTSXFRCUNWJOSBV6K","short_pith_number":"pith:UM243XLP","schema_version":"1.0","canonical_sha256":"a335cddd6fde672b9622a36c974835f2aa2f2a0081ed2766208c11e6b0828021","source":{"kind":"arxiv","id":"2203.09481","version":5},"attestation_state":"computed","paper":{"title":"Diffusion Probabilistic Modeling for Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Prakhar Srivastava, Ruihan Yang, Stephan Mandt","submitted_at":"2022-03-16T03:52:45Z","abstract_excerpt":"Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in perceptual and probabilistic forecasting metrics. We propose an autoregressive, end-to-end optimized video diffusion model inspired by recent advances in neural video compression. The model successively generates future frames by correcting a deterministic next-frame prediction using a stochastic residual generated by an inverse diffusion process. We compare "},"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":"2203.09481","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-16T03:52:45Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"266a15d1fb3419dc80bfe473af630eaaee5df5a022943b45c91c8872327daa4f","abstract_canon_sha256":"b44c863bbdadced0b183b9b6c721491dd9e05a0ae537ad45969b0fa29c4be2fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:30.096810Z","signature_b64":"UEEiwO/Ff7c8A8r9q2piyiHCQdTCl42binwURjzSX5TXh7WwaF/u0DaOI6mGaZikvXAqG8SqXRX6qYe4i5eRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a335cddd6fde672b9622a36c974835f2aa2f2a0081ed2766208c11e6b0828021","last_reissued_at":"2026-07-05T05:23:30.096387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:30.096387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Probabilistic Modeling for Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Prakhar Srivastava, Ruihan Yang, Stephan Mandt","submitted_at":"2022-03-16T03:52:45Z","abstract_excerpt":"Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in perceptual and probabilistic forecasting metrics. We propose an autoregressive, end-to-end optimized video diffusion model inspired by recent advances in neural video compression. The model successively generates future frames by correcting a deterministic next-frame prediction using a stochastic residual generated by an inverse diffusion process. We compare "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09481","kind":"arxiv","version":5},"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/2203.09481/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":"2203.09481","created_at":"2026-07-05T05:23:30.096444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09481v5","created_at":"2026-07-05T05:23:30.096444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09481","created_at":"2026-07-05T05:23:30.096444+00:00"},{"alias_kind":"pith_short_12","alias_value":"UM243XLP3ZTS","created_at":"2026-07-05T05:23:30.096444+00:00"},{"alias_kind":"pith_short_16","alias_value":"UM243XLP3ZTSXFRC","created_at":"2026-07-05T05:23:30.096444+00:00"},{"alias_kind":"pith_short_8","alias_value":"UM243XLP","created_at":"2026-07-05T05:23:30.096444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31050","citing_title":"Learning Video Dynamics with Predictive Differentiable Rendering","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04145","citing_title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2210.02399","citing_title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2211.01324","citing_title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2204.03458","citing_title":"Video Diffusion Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2308.06571","citing_title":"ModelScope Text-to-Video Technical Report","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2210.02303","citing_title":"Imagen Video: High Definition Video Generation with Diffusion Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K","json":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K.json","graph_json":"https://pith.science/api/pith-number/UM243XLP3ZTSXFRCUNWJOSBV6K/graph.json","events_json":"https://pith.science/api/pith-number/UM243XLP3ZTSXFRCUNWJOSBV6K/events.json","paper":"https://pith.science/paper/UM243XLP"},"agent_actions":{"view_html":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K","download_json":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K.json","view_paper":"https://pith.science/paper/UM243XLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09481&json=true","fetch_graph":"https://pith.science/api/pith-number/UM243XLP3ZTSXFRCUNWJOSBV6K/graph.json","fetch_events":"https://pith.science/api/pith-number/UM243XLP3ZTSXFRCUNWJOSBV6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K/action/storage_attestation","attest_author":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K/action/author_attestation","sign_citation":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K/action/citation_signature","submit_replication":"https://pith.science/pith/UM243XLP3ZTSXFRCUNWJOSBV6K/action/replication_record"}},"created_at":"2026-07-05T05:23:30.096444+00:00","updated_at":"2026-07-05T05:23:30.096444+00:00"}