{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LZP5ZLB5INHL7XKSBL53BYNNRZ","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":"66d9ce47900444a9df277117dc43073abfeb345146363eb621a3eba8847d7409","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T11:06:15Z","title_canon_sha256":"6adc0ab111147e73a2b6cfd50b27e06d1c0d0783f80332e23aed7ad005476ac8"},"schema_version":"1.0","source":{"id":"2305.10874","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10874","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10874v4","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10874","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"LZP5ZLB5INHL","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"LZP5ZLB5INHL7XKS","created_at":"2026-07-05T08:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"LZP5ZLB5","created_at":"2026-07-05T08:11:38Z"}],"graph_snapshots":[{"event_id":"sha256:88f402f1b84bdb95d6b213b1ca0466779adc5d9b06752f5e103a5bb2809781a1","target":"graph","created_at":"2026-07-05T08:11:38Z","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/2305.10874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huan Yang, Huiguo He, Jianlong Fu, Jiaying Liu, Junchen Zhu, Wenjing Wang, Zixi Tuo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T11:06:15Z","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10874","kind":"arxiv","version":4},"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":"sha256:9e72821a3f9ba4e04141c35ceff7208f330352d14bb40b97dc25fca2e11cbd83","target":"record","created_at":"2026-07-05T08:11:38Z","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":"66d9ce47900444a9df277117dc43073abfeb345146363eb621a3eba8847d7409","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T11:06:15Z","title_canon_sha256":"6adc0ab111147e73a2b6cfd50b27e06d1c0d0783f80332e23aed7ad005476ac8"},"schema_version":"1.0","source":{"id":"2305.10874","kind":"arxiv","version":4}},"canonical_sha256":"5e5fdcac3d434ebfdd520afbb0e1ad8e79c746bd6508b676220ef6d73e418271","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e5fdcac3d434ebfdd520afbb0e1ad8e79c746bd6508b676220ef6d73e418271","first_computed_at":"2026-07-05T08:11:38.787644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:38.787644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cmkMoIAAbEvfCjJ2zIcKAdpK1EJPkjaJRUeMKNIDwWPmtQ7rGU8MVsVnRv24cpezY/Rmbw2x0ophDJ5G0XCQBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:38.788057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10874","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e72821a3f9ba4e04141c35ceff7208f330352d14bb40b97dc25fca2e11cbd83","sha256:88f402f1b84bdb95d6b213b1ca0466779adc5d9b06752f5e103a5bb2809781a1"],"state_sha256":"e6e9e8f0ce5680df92775f1bbe740fb2437abe94c55fe5c17d823403da40e580"}