{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JPS75QUZKGEXWJIUQZHH6VAWM6","short_pith_number":"pith:JPS75QUZ","schema_version":"1.0","canonical_sha256":"4be5fec29951897b2514864e7f5416678067157111751ad32180ec43b520d954","source":{"kind":"arxiv","id":"2412.11710","version":1},"attestation_state":"computed","paper":{"title":"Re-Attentional Controllable Video Diffusion Editing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Antoni B. Chan, Mengyi Liu, Xiaoya Zhang, Xin Liu, Yong Li, Yuanzhi Wang, Zhen Cui","submitted_at":"2024-12-16T12:32:21Z","abstract_excerpt":"Editing videos with textual guidance has garnered popularity due to its streamlined process which mandates users to solely edit the text prompt corresponding to the source video. Recent studies have explored and exploited large-scale text-to-image diffusion models for text-guided video editing, resulting in remarkable video editing capabilities. However, they may still suffer from some limitations such as mislocated objects, incorrect number of objects. Therefore, the controllability of video editing remains a formidable challenge. In this paper, we aim to challenge the above limitations by pr"},"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":"2412.11710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T12:32:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1c2ea13a36e9a31bb20b4ae4edd63fb276fdf99c853ef116ea899aba81d8d45","abstract_canon_sha256":"9cba86170d01d5699a133364a13d75df445fb2d7c01141a8e808006966977096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:50.484710Z","signature_b64":"Szefead6m+Z+PAZnXTapTLsH0oTDVc0kMrwvTcuVUBp2LZ83/hgK9P5bV2eW3mZScwwmFusSqZPegSR1N5STCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4be5fec29951897b2514864e7f5416678067157111751ad32180ec43b520d954","last_reissued_at":"2026-07-05T09:49:50.484192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:50.484192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re-Attentional Controllable Video Diffusion Editing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Antoni B. Chan, Mengyi Liu, Xiaoya Zhang, Xin Liu, Yong Li, Yuanzhi Wang, Zhen Cui","submitted_at":"2024-12-16T12:32:21Z","abstract_excerpt":"Editing videos with textual guidance has garnered popularity due to its streamlined process which mandates users to solely edit the text prompt corresponding to the source video. Recent studies have explored and exploited large-scale text-to-image diffusion models for text-guided video editing, resulting in remarkable video editing capabilities. However, they may still suffer from some limitations such as mislocated objects, incorrect number of objects. Therefore, the controllability of video editing remains a formidable challenge. In this paper, we aim to challenge the above limitations by pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11710","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/2412.11710/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":"2412.11710","created_at":"2026-07-05T09:49:50.484256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11710v1","created_at":"2026-07-05T09:49:50.484256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11710","created_at":"2026-07-05T09:49:50.484256+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPS75QUZKGEX","created_at":"2026-07-05T09:49:50.484256+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPS75QUZKGEXWJIU","created_at":"2026-07-05T09:49:50.484256+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPS75QUZ","created_at":"2026-07-05T09:49:50.484256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23245","citing_title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02438","citing_title":"Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6","json":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6.json","graph_json":"https://pith.science/api/pith-number/JPS75QUZKGEXWJIUQZHH6VAWM6/graph.json","events_json":"https://pith.science/api/pith-number/JPS75QUZKGEXWJIUQZHH6VAWM6/events.json","paper":"https://pith.science/paper/JPS75QUZ"},"agent_actions":{"view_html":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6","download_json":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6.json","view_paper":"https://pith.science/paper/JPS75QUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11710&json=true","fetch_graph":"https://pith.science/api/pith-number/JPS75QUZKGEXWJIUQZHH6VAWM6/graph.json","fetch_events":"https://pith.science/api/pith-number/JPS75QUZKGEXWJIUQZHH6VAWM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6/action/storage_attestation","attest_author":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6/action/author_attestation","sign_citation":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6/action/citation_signature","submit_replication":"https://pith.science/pith/JPS75QUZKGEXWJIUQZHH6VAWM6/action/replication_record"}},"created_at":"2026-07-05T09:49:50.484256+00:00","updated_at":"2026-07-05T09:49:50.484256+00:00"}