{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PC4C364TJHREJJXIQ76Y536HZO","short_pith_number":"pith:PC4C364T","schema_version":"1.0","canonical_sha256":"78b82dfb9349e244a6e887fd8eefc7cbb9c88c20952ed101af902a084a48fbcf","source":{"kind":"arxiv","id":"2206.07696","version":3},"attestation_state":"computed","paper":{"title":"Diffusion Models for Video Prediction and Infilling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Dittadi, Arash Mehrjou, Didrik Nielsen, Stefan Bauer, Tobias H\\\"oppe","submitted_at":"2022-06-15T17:44:47Z","abstract_excerpt":"Predicting and anticipating future outcomes or reasoning about missing information in a sequence are critical skills for agents to be able to make intelligent decisions. This requires strong, temporally coherent generative capabilities. Diffusion models have shown remarkable success in several generative tasks, but have not been extensively explored in the video domain. We present Random-Mask Video Diffusion (RaMViD), which extends image diffusion models to videos using 3D convolutions, and introduces a new conditioning technique during training. By varying the mask we condition on, the model "},"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":"2206.07696","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T17:44:47Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"22274421b7820b7a09c62fcf1e303138262543d9545b047452b6b91b31214320","abstract_canon_sha256":"f87710f28e133525371b40bee18dd3ee8f3ed949125e68b99c24ab8f0aaf8b07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:40.811984Z","signature_b64":"0O/zAgcnkVZCOc6fMSLWCr7fZoMvUuzYBUtQ4I4fSfSq1RI6NePv3Be6vm/CDm7kLuEW2pj+i/EayEG62jsRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78b82dfb9349e244a6e887fd8eefc7cbb9c88c20952ed101af902a084a48fbcf","last_reissued_at":"2026-07-05T05:15:40.811384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:40.811384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Models for Video Prediction and Infilling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrea Dittadi, Arash Mehrjou, Didrik Nielsen, Stefan Bauer, Tobias H\\\"oppe","submitted_at":"2022-06-15T17:44:47Z","abstract_excerpt":"Predicting and anticipating future outcomes or reasoning about missing information in a sequence are critical skills for agents to be able to make intelligent decisions. This requires strong, temporally coherent generative capabilities. Diffusion models have shown remarkable success in several generative tasks, but have not been extensively explored in the video domain. We present Random-Mask Video Diffusion (RaMViD), which extends image diffusion models to videos using 3D convolutions, and introduces a new conditioning technique during training. By varying the mask we condition on, the model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07696","kind":"arxiv","version":3},"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/2206.07696/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":"2206.07696","created_at":"2026-07-05T05:15:40.811443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07696v3","created_at":"2026-07-05T05:15:40.811443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07696","created_at":"2026-07-05T05:15:40.811443+00:00"},{"alias_kind":"pith_short_12","alias_value":"PC4C364TJHRE","created_at":"2026-07-05T05:15:40.811443+00:00"},{"alias_kind":"pith_short_16","alias_value":"PC4C364TJHREJJXI","created_at":"2026-07-05T05:15:40.811443+00:00"},{"alias_kind":"pith_short_8","alias_value":"PC4C364T","created_at":"2026-07-05T05:15:40.811443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31204","citing_title":"Probabilistic Precipitation Nowcasting with Rectified Flow Transformers","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13942","citing_title":"Frozen Forecasting: A Unified Evaluation","ref_index":17,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2210.02399","citing_title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19325","citing_title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2310.05737","citing_title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2308.06571","citing_title":"ModelScope Text-to-Video Technical Report","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO","json":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO.json","graph_json":"https://pith.science/api/pith-number/PC4C364TJHREJJXIQ76Y536HZO/graph.json","events_json":"https://pith.science/api/pith-number/PC4C364TJHREJJXIQ76Y536HZO/events.json","paper":"https://pith.science/paper/PC4C364T"},"agent_actions":{"view_html":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO","download_json":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO.json","view_paper":"https://pith.science/paper/PC4C364T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07696&json=true","fetch_graph":"https://pith.science/api/pith-number/PC4C364TJHREJJXIQ76Y536HZO/graph.json","fetch_events":"https://pith.science/api/pith-number/PC4C364TJHREJJXIQ76Y536HZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO/action/storage_attestation","attest_author":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO/action/author_attestation","sign_citation":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO/action/citation_signature","submit_replication":"https://pith.science/pith/PC4C364TJHREJJXIQ76Y536HZO/action/replication_record"}},"created_at":"2026-07-05T05:15:40.811443+00:00","updated_at":"2026-07-05T05:15:40.811443+00:00"}