{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E64ORHKDHTNNJDAPIK7CT5APQG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5c9ed04b20fa26f1d1cdc075fce9e4dbe02e39141f5fee931c614ff0a0c175ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-10T04:26:32Z","title_canon_sha256":"95bfe1bd67af25d5cf8f9f265cf1a9cff0027442da8f0bc006699ad58925d3cf"},"schema_version":"1.0","source":{"id":"2212.05199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05199","created_at":"2026-07-05T05:58:18Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05199v2","created_at":"2026-07-05T05:58:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05199","created_at":"2026-07-05T05:58:18Z"},{"alias_kind":"pith_short_12","alias_value":"E64ORHKDHTNN","created_at":"2026-07-05T05:58:18Z"},{"alias_kind":"pith_short_16","alias_value":"E64ORHKDHTNNJDAP","created_at":"2026-07-05T05:58:18Z"},{"alias_kind":"pith_short_8","alias_value":"E64ORHKD","created_at":"2026-07-05T05:58:18Z"}],"graph_snapshots":[{"event_id":"sha256:6fa736f53c7c316cde2b6b8ca77b8802caaf1498921eda822cd54642f6e311cf","target":"graph","created_at":"2026-07-05T05:58:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2212.05199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging","authors_text":"Alexander G. Hauptmann, Han Zhang, Huiwen Chang, Irfan Essa, Jos\\'e Lezama, Kihyuk Sohn, Lijun Yu, Lu Jiang, Ming-Hsuan Yang, Yong Cheng, Yuan Hao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-10T04:26:32Z","title":"MAGVIT: Masked Generative Video Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05199","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a505e8deab564d7ad5b3a542f7276d04583d4d1aa9d02dc01495a7f9d8a35473","target":"record","created_at":"2026-07-05T05:58:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5c9ed04b20fa26f1d1cdc075fce9e4dbe02e39141f5fee931c614ff0a0c175ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-10T04:26:32Z","title_canon_sha256":"95bfe1bd67af25d5cf8f9f265cf1a9cff0027442da8f0bc006699ad58925d3cf"},"schema_version":"1.0","source":{"id":"2212.05199","kind":"arxiv","version":2}},"canonical_sha256":"27b8e89d433cdad48c0f42be29f40f81977068367f1e88e2af1fbc79eddda5af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27b8e89d433cdad48c0f42be29f40f81977068367f1e88e2af1fbc79eddda5af","first_computed_at":"2026-07-05T05:58:18.601100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:18.601100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z8bCmefCRkH4kY9RG0OTnPGfBz9m5sY4BUnMDM9Ob8DHnaoRAnSUY/7t1jPzuPaZPbSPhGb6UzKRJPHfZMUWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:18.601657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.05199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a505e8deab564d7ad5b3a542f7276d04583d4d1aa9d02dc01495a7f9d8a35473","sha256:6fa736f53c7c316cde2b6b8ca77b8802caaf1498921eda822cd54642f6e311cf"],"state_sha256":"43ae59c5bb5b6fef8a5b611ecd3af5a85b6dec784188c6b393e195e4ae7836c0"}