{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TYLU7LGTRHYSA6OJZPVU6KKCEU","short_pith_number":"pith:TYLU7LGT","schema_version":"1.0","canonical_sha256":"9e174facd389f12079c9cbeb4f29422515cf6def17007e611b74cc038cc175c0","source":{"kind":"arxiv","id":"2204.03638","version":4},"attestation_state":"computed","paper":{"title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"David Jacobs, Devi Parikh, Guan Pang, Harry Yang, Jia-Bin Huang, Songwei Ge, Thomas Hayes, Xi Yin","submitted_at":"2022-04-07T17:59:02Z","abstract_excerpt":"Videos are created to express emotion, exchange information, and share experiences. Video synthesis has intrigued researchers for a long time. Despite the rapid progress driven by advances in visual synthesis, most existing studies focus on improving the frames' quality and the transitions between them, while little progress has been made in generating longer videos. In this paper, we present a method that builds on 3D-VQGAN and transformers to generate videos with thousands of frames. Our evaluation shows that our model trained on 16-frame video clips from standard benchmarks such as UCF-101,"},"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":"2204.03638","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:59:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfdc06c1cc680141632d839508c5c7be01afd0957736e7485054258fe2caaf10","abstract_canon_sha256":"8221a07e225c78c45d2eb341fa3cd832d4cc258b57f78c693f84ad9de4b3c212"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:41.550137Z","signature_b64":"MMG+2XDqUSw7sOp15vEfCPJbpS2b+RArxQDN7KoBCFUeH4W1g2NrFbswUHx/o9hvdKzAGL34PVgg8lnKaeq+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e174facd389f12079c9cbeb4f29422515cf6def17007e611b74cc038cc175c0","last_reissued_at":"2026-07-05T05:00:41.549654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:41.549654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"David Jacobs, Devi Parikh, Guan Pang, Harry Yang, Jia-Bin Huang, Songwei Ge, Thomas Hayes, Xi Yin","submitted_at":"2022-04-07T17:59:02Z","abstract_excerpt":"Videos are created to express emotion, exchange information, and share experiences. Video synthesis has intrigued researchers for a long time. Despite the rapid progress driven by advances in visual synthesis, most existing studies focus on improving the frames' quality and the transitions between them, while little progress has been made in generating longer videos. In this paper, we present a method that builds on 3D-VQGAN and transformers to generate videos with thousands of frames. Our evaluation shows that our model trained on 16-frame video clips from standard benchmarks such as UCF-101,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03638","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/2204.03638/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":"2204.03638","created_at":"2026-07-05T05:00:41.549714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03638v4","created_at":"2026-07-05T05:00:41.549714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03638","created_at":"2026-07-05T05:00:41.549714+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYLU7LGTRHYS","created_at":"2026-07-05T05:00:41.549714+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYLU7LGTRHYSA6OJ","created_at":"2026-07-05T05:00:41.549714+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYLU7LGT","created_at":"2026-07-05T05:00:41.549714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11096","citing_title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2211.13221","citing_title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2205.15868","citing_title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU","json":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU.json","graph_json":"https://pith.science/api/pith-number/TYLU7LGTRHYSA6OJZPVU6KKCEU/graph.json","events_json":"https://pith.science/api/pith-number/TYLU7LGTRHYSA6OJZPVU6KKCEU/events.json","paper":"https://pith.science/paper/TYLU7LGT"},"agent_actions":{"view_html":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU","download_json":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU.json","view_paper":"https://pith.science/paper/TYLU7LGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03638&json=true","fetch_graph":"https://pith.science/api/pith-number/TYLU7LGTRHYSA6OJZPVU6KKCEU/graph.json","fetch_events":"https://pith.science/api/pith-number/TYLU7LGTRHYSA6OJZPVU6KKCEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU/action/storage_attestation","attest_author":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU/action/author_attestation","sign_citation":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU/action/citation_signature","submit_replication":"https://pith.science/pith/TYLU7LGTRHYSA6OJZPVU6KKCEU/action/replication_record"}},"created_at":"2026-07-05T05:00:41.549714+00:00","updated_at":"2026-07-05T05:00:41.549714+00:00"}