{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LZP5ZLB5INHL7XKSBL53BYNNRZ","short_pith_number":"pith:LZP5ZLB5","schema_version":"1.0","canonical_sha256":"5e5fdcac3d434ebfdd520afbb0e1ad8e79c746bd6508b676220ef6d73e418271","source":{"kind":"arxiv","id":"2305.10874","version":4},"attestation_state":"computed","paper":{"title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huan Yang, Huiguo He, Jianlong Fu, Jiaying Liu, Junchen Zhu, Wenjing Wang, Zixi Tuo","submitted_at":"2023-05-18T11:06:15Z","abstract_excerpt":"With the explosive popularity of AI-generated content (AIGC), video generation has recently received a lot of attention. Generating videos guided by text instructions poses significant challenges, such as modeling the complex relationship between space and time, and the lack of large-scale text-video paired data. Existing text-video datasets suffer from limitations in both content quality and scale, or they are not open-source, rendering them inaccessible for study and use. For model design, previous approaches extend pretrained text-to-image generation models by adding temporal 1D convolution"},"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":"2305.10874","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T11:06:15Z","cross_cats_sorted":[],"title_canon_sha256":"6adc0ab111147e73a2b6cfd50b27e06d1c0d0783f80332e23aed7ad005476ac8","abstract_canon_sha256":"66d9ce47900444a9df277117dc43073abfeb345146363eb621a3eba8847d7409"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:38.788057Z","signature_b64":"cmkMoIAAbEvfCjJ2zIcKAdpK1EJPkjaJRUeMKNIDwWPmtQ7rGU8MVsVnRv24cpezY/Rmbw2x0ophDJ5G0XCQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e5fdcac3d434ebfdd520afbb0e1ad8e79c746bd6508b676220ef6d73e418271","last_reissued_at":"2026-07-05T08:11:38.787644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:38.787644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huan Yang, Huiguo He, Jianlong Fu, Jiaying Liu, Junchen Zhu, Wenjing Wang, Zixi Tuo","submitted_at":"2023-05-18T11:06:15Z","abstract_excerpt":"With the explosive popularity of AI-generated content (AIGC), video generation has recently received a lot of attention. Generating videos guided by text instructions poses significant challenges, such as modeling the complex relationship between space and time, and the lack of large-scale text-video paired data. Existing text-video datasets suffer from limitations in both content quality and scale, or they are not open-source, rendering them inaccessible for study and use. For model design, previous approaches extend pretrained text-to-image generation models by adding temporal 1D convolution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10874","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/2305.10874/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":"2305.10874","created_at":"2026-07-05T08:11:38.787705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10874v4","created_at":"2026-07-05T08:11:38.787705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10874","created_at":"2026-07-05T08:11:38.787705+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZP5ZLB5INHL","created_at":"2026-07-05T08:11:38.787705+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZP5ZLB5INHL7XKS","created_at":"2026-07-05T08:11:38.787705+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZP5ZLB5","created_at":"2026-07-05T08:11:38.787705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.03520","citing_title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02799","citing_title":"UNICA: A Unified Neural Framework for Controllable 3D Avatars","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05895","citing_title":"Detecting AI-Generated Videos with Spiking Neural Networks","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ","json":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ.json","graph_json":"https://pith.science/api/pith-number/LZP5ZLB5INHL7XKSBL53BYNNRZ/graph.json","events_json":"https://pith.science/api/pith-number/LZP5ZLB5INHL7XKSBL53BYNNRZ/events.json","paper":"https://pith.science/paper/LZP5ZLB5"},"agent_actions":{"view_html":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ","download_json":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ.json","view_paper":"https://pith.science/paper/LZP5ZLB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10874&json=true","fetch_graph":"https://pith.science/api/pith-number/LZP5ZLB5INHL7XKSBL53BYNNRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LZP5ZLB5INHL7XKSBL53BYNNRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ/action/storage_attestation","attest_author":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ/action/author_attestation","sign_citation":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ/action/citation_signature","submit_replication":"https://pith.science/pith/LZP5ZLB5INHL7XKSBL53BYNNRZ/action/replication_record"}},"created_at":"2026-07-05T08:11:38.787705+00:00","updated_at":"2026-07-05T08:11:38.787705+00:00"}