{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CBQIJZKSWVDCLYIVAHPJXRCBLE","short_pith_number":"pith:CBQIJZKS","schema_version":"1.0","canonical_sha256":"106084e552b54625e11501de9bc441593e6a7b342a3e240519f54c27e2bb7725","source":{"kind":"arxiv","id":"2205.09853","version":4},"attestation_state":"computed","paper":{"title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexia Jolicoeur-Martineau, Christopher Pal, Vikram Voleti","submitted_at":"2022-05-19T20:58:05Z","abstract_excerpt":"Video prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor and generalization beyond the training data is difficult. Furthermore, existing prediction frameworks are typically not capable of simultaneously handling other video-related tasks such as unconditional generation or interpolation. In this work, we devise a general-purpose framework called Masked Conditional Video Diffusion (MCVD) for all of these video synthesis tasks using a probabilistic conditional score-based denoising diffusion model, conditioned on "},"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":"2205.09853","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T20:58:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e5319a8362391de37a920887b13722f10e5bcfd9735a7c4425e876e6ef0a668c","abstract_canon_sha256":"329b84add57a4e204bcedebf2bdfd620e2a517403ff26c0799b5263797408421"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:11.829037Z","signature_b64":"7gI+38pBwHfSAge2f+zK741Y3pcya7zIuffVU99uSD0GMnYCfBVb96WK3uo94jK8MP52l3YVR8tSJw+yiFBnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"106084e552b54625e11501de9bc441593e6a7b342a3e240519f54c27e2bb7725","last_reissued_at":"2026-07-05T05:06:11.828564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:11.828564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexia Jolicoeur-Martineau, Christopher Pal, Vikram Voleti","submitted_at":"2022-05-19T20:58:05Z","abstract_excerpt":"Video prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor and generalization beyond the training data is difficult. Furthermore, existing prediction frameworks are typically not capable of simultaneously handling other video-related tasks such as unconditional generation or interpolation. In this work, we devise a general-purpose framework called Masked Conditional Video Diffusion (MCVD) for all of these video synthesis tasks using a probabilistic conditional score-based denoising diffusion model, conditioned on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09853","kind":"arxiv","version":4},"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/2205.09853/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":"2205.09853","created_at":"2026-07-05T05:06:11.828617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09853v4","created_at":"2026-07-05T05:06:11.828617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09853","created_at":"2026-07-05T05:06:11.828617+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBQIJZKSWVDC","created_at":"2026-07-05T05:06:11.828617+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBQIJZKSWVDCLYIV","created_at":"2026-07-05T05:06:11.828617+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBQIJZKS","created_at":"2026-07-05T05:06:11.828617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.02311","citing_title":"Inferring Dynamic Physical Properties from Video Foundation Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2210.02399","citing_title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2211.13221","citing_title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE","json":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE.json","graph_json":"https://pith.science/api/pith-number/CBQIJZKSWVDCLYIVAHPJXRCBLE/graph.json","events_json":"https://pith.science/api/pith-number/CBQIJZKSWVDCLYIVAHPJXRCBLE/events.json","paper":"https://pith.science/paper/CBQIJZKS"},"agent_actions":{"view_html":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE","download_json":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE.json","view_paper":"https://pith.science/paper/CBQIJZKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09853&json=true","fetch_graph":"https://pith.science/api/pith-number/CBQIJZKSWVDCLYIVAHPJXRCBLE/graph.json","fetch_events":"https://pith.science/api/pith-number/CBQIJZKSWVDCLYIVAHPJXRCBLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE/action/storage_attestation","attest_author":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE/action/author_attestation","sign_citation":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE/action/citation_signature","submit_replication":"https://pith.science/pith/CBQIJZKSWVDCLYIVAHPJXRCBLE/action/replication_record"}},"created_at":"2026-07-05T05:06:11.828617+00:00","updated_at":"2026-07-05T05:06:11.828617+00:00"}