{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UGDL4IJQFW7VMDJQTZK523CCJU","short_pith_number":"pith:UGDL4IJQ","schema_version":"1.0","canonical_sha256":"a186be21302dbf560d309e55dd6c424d2c981aca67dcd7f1ee65d94e41adf1ff","source":{"kind":"arxiv","id":"2403.02332","version":4},"attestation_state":"computed","paper":{"title":"UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Sihan Xu, Tian Xia, Xuweiyi Chen","submitted_at":"2024-03-04T18:58:11Z","abstract_excerpt":"Video Diffusion Models have been developed for video generation, usually integrating text and image conditioning to enhance control over the generated content. Despite the progress, ensuring consistency across frames remains a challenge, particularly when using text prompts as control conditions. To address this problem, we introduce UniCtrl, a novel, plug-and-play method that is universally applicable to improve the spatiotemporal consistency and motion diversity of videos generated by text-to-video models without additional training. UniCtrl ensures semantic consistency across different fram"},"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":"2403.02332","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T18:58:11Z","cross_cats_sorted":[],"title_canon_sha256":"21b38215328d0caa98e61c427bdcf2910e08c775adb2a804d95fab7433a5b92a","abstract_canon_sha256":"a2054bf472c3d1d0ea53d417dfae1375c41a4d9170c8bbc2620c0bc7df79d8f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:29.450533Z","signature_b64":"4qNTDCRnSj1I+GR0ZiYnJ03kFxkUlXlKHFQ4Lbn0NwEnw8ZnyS5XWl76VUj69/xVsS+PNsshh70NM4eK8sHCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a186be21302dbf560d309e55dd6c424d2c981aca67dcd7f1ee65d94e41adf1ff","last_reissued_at":"2026-07-05T09:33:29.450046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:29.450046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Sihan Xu, Tian Xia, Xuweiyi Chen","submitted_at":"2024-03-04T18:58:11Z","abstract_excerpt":"Video Diffusion Models have been developed for video generation, usually integrating text and image conditioning to enhance control over the generated content. Despite the progress, ensuring consistency across frames remains a challenge, particularly when using text prompts as control conditions. To address this problem, we introduce UniCtrl, a novel, plug-and-play method that is universally applicable to improve the spatiotemporal consistency and motion diversity of videos generated by text-to-video models without additional training. UniCtrl ensures semantic consistency across different fram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02332","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/2403.02332/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":"2403.02332","created_at":"2026-07-05T09:33:29.450105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02332v4","created_at":"2026-07-05T09:33:29.450105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02332","created_at":"2026-07-05T09:33:29.450105+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGDL4IJQFW7V","created_at":"2026-07-05T09:33:29.450105+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGDL4IJQFW7VMDJQ","created_at":"2026-07-05T09:33:29.450105+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGDL4IJQ","created_at":"2026-07-05T09:33:29.450105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01792","citing_title":"CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU","json":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU.json","graph_json":"https://pith.science/api/pith-number/UGDL4IJQFW7VMDJQTZK523CCJU/graph.json","events_json":"https://pith.science/api/pith-number/UGDL4IJQFW7VMDJQTZK523CCJU/events.json","paper":"https://pith.science/paper/UGDL4IJQ"},"agent_actions":{"view_html":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU","download_json":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU.json","view_paper":"https://pith.science/paper/UGDL4IJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02332&json=true","fetch_graph":"https://pith.science/api/pith-number/UGDL4IJQFW7VMDJQTZK523CCJU/graph.json","fetch_events":"https://pith.science/api/pith-number/UGDL4IJQFW7VMDJQTZK523CCJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU/action/storage_attestation","attest_author":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU/action/author_attestation","sign_citation":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU/action/citation_signature","submit_replication":"https://pith.science/pith/UGDL4IJQFW7VMDJQTZK523CCJU/action/replication_record"}},"created_at":"2026-07-05T09:33:29.450105+00:00","updated_at":"2026-07-05T09:33:29.450105+00:00"}