{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YVYQU3QOSC2SF6EGZJBMTNELFJ","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":"3cd8e92df925d317066dbdaf82005109018c3f460507daf70212300765e9534c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:59:57Z","title_canon_sha256":"d807b7cef78986cd9a29cec12be5efb51e5ace7ebe677630560df23fa10e60d2"},"schema_version":"1.0","source":{"id":"2312.06662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06662","created_at":"2026-07-05T07:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06662v1","created_at":"2026-07-05T07:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06662","created_at":"2026-07-05T07:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"YVYQU3QOSC2S","created_at":"2026-07-05T07:22:48Z"},{"alias_kind":"pith_short_16","alias_value":"YVYQU3QOSC2SF6EG","created_at":"2026-07-05T07:22:48Z"},{"alias_kind":"pith_short_8","alias_value":"YVYQU3QO","created_at":"2026-07-05T07:22:48Z"}],"graph_snapshots":[{"event_id":"sha256:41f6fb1a3bd7ec778ea465288880e51172460170357a0a8ff68dd2e45e0d52a8","target":"graph","created_at":"2026-07-05T07:22:48Z","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/2312.06662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image ","authors_text":"Agrim Gupta, Irfan Essa, Jos\\'e Lezama, Kihyuk Sohn, Li Fei-Fei, Lijun Yu, Lu Jiang, Meera Hahn, Xiuye Gu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:59:57Z","title":"Photorealistic Video Generation with Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06662","kind":"arxiv","version":1},"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":"sha256:26f09ba503e22c779f3a31638fb37e06b29031c84fdacd423d9bfdad612ed975","target":"record","created_at":"2026-07-05T07:22:48Z","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":"3cd8e92df925d317066dbdaf82005109018c3f460507daf70212300765e9534c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:59:57Z","title_canon_sha256":"d807b7cef78986cd9a29cec12be5efb51e5ace7ebe677630560df23fa10e60d2"},"schema_version":"1.0","source":{"id":"2312.06662","kind":"arxiv","version":1}},"canonical_sha256":"c5710a6e0e90b522f886ca42c9b48b2a469e610f955f032d6a1f0ac904990c1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5710a6e0e90b522f886ca42c9b48b2a469e610f955f032d6a1f0ac904990c1d","first_computed_at":"2026-07-05T07:22:48.497362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:48.497362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XnXLFgffUJO+M0VUqU8CLgI/stNZMtNwqKCwOW4s4g7O6XfUEFo7ujmvUPBJMhoN/WvB0cfmOKN8Ap0gRX8UDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:48.497807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26f09ba503e22c779f3a31638fb37e06b29031c84fdacd423d9bfdad612ed975","sha256:41f6fb1a3bd7ec778ea465288880e51172460170357a0a8ff68dd2e45e0d52a8"],"state_sha256":"5c0cf9803386a6678bc5eac27c2c5b6d470cc1ad6dbf3a501d0a20366a26e4c5"}