{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YVYQU3QOSC2SF6EGZJBMTNELFJ","short_pith_number":"pith:YVYQU3QO","schema_version":"1.0","canonical_sha256":"c5710a6e0e90b522f886ca42c9b48b2a469e610f955f032d6a1f0ac904990c1d","source":{"kind":"arxiv","id":"2312.06662","version":1},"attestation_state":"computed","paper":{"title":"Photorealistic Video Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Agrim Gupta, Irfan Essa, Jos\\'e Lezama, Kihyuk Sohn, Li Fei-Fei, Lijun Yu, Lu Jiang, Meera Hahn, Xiuye Gu","submitted_at":"2023-12-11T18:59:57Z","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 "},"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":"2312.06662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T18:59:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d807b7cef78986cd9a29cec12be5efb51e5ace7ebe677630560df23fa10e60d2","abstract_canon_sha256":"3cd8e92df925d317066dbdaf82005109018c3f460507daf70212300765e9534c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:48.497807Z","signature_b64":"XnXLFgffUJO+M0VUqU8CLgI/stNZMtNwqKCwOW4s4g7O6XfUEFo7ujmvUPBJMhoN/WvB0cfmOKN8Ap0gRX8UDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5710a6e0e90b522f886ca42c9b48b2a469e610f955f032d6a1f0ac904990c1d","last_reissued_at":"2026-07-05T07:22:48.497362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:48.497362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Photorealistic Video Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Agrim Gupta, Irfan Essa, Jos\\'e Lezama, Kihyuk Sohn, Li Fei-Fei, Lijun Yu, Lu Jiang, Meera Hahn, Xiuye Gu","submitted_at":"2023-12-11T18:59:57Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06662","kind":"arxiv","version":1},"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/2312.06662/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":"2312.06662","created_at":"2026-07-05T07:22:48.497420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06662v1","created_at":"2026-07-05T07:22:48.497420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06662","created_at":"2026-07-05T07:22:48.497420+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVYQU3QOSC2S","created_at":"2026-07-05T07:22:48.497420+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVYQU3QOSC2SF6EG","created_at":"2026-07-05T07:22:48.497420+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVYQU3QO","created_at":"2026-07-05T07:22:48.497420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13501","citing_title":"GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13501","citing_title":"GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18576","citing_title":"DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20780","citing_title":"Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2408.14837","citing_title":"Diffusion Models Are Real-Time Game Engines","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14125","citing_title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12011","citing_title":"CaloArt: Large-Patch x-Prediction Diffusion Transformers for High-Granularity Calorimeter Shower Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ","json":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ.json","graph_json":"https://pith.science/api/pith-number/YVYQU3QOSC2SF6EGZJBMTNELFJ/graph.json","events_json":"https://pith.science/api/pith-number/YVYQU3QOSC2SF6EGZJBMTNELFJ/events.json","paper":"https://pith.science/paper/YVYQU3QO"},"agent_actions":{"view_html":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ","download_json":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ.json","view_paper":"https://pith.science/paper/YVYQU3QO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06662&json=true","fetch_graph":"https://pith.science/api/pith-number/YVYQU3QOSC2SF6EGZJBMTNELFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YVYQU3QOSC2SF6EGZJBMTNELFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ/action/storage_attestation","attest_author":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ/action/author_attestation","sign_citation":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ/action/citation_signature","submit_replication":"https://pith.science/pith/YVYQU3QOSC2SF6EGZJBMTNELFJ/action/replication_record"}},"created_at":"2026-07-05T07:22:48.497420+00:00","updated_at":"2026-07-05T07:22:48.497420+00:00"}