{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JX23ZRDN6BBALAGG7FOAUTWDEV","short_pith_number":"pith:JX23ZRDN","schema_version":"1.0","canonical_sha256":"4df5bcc46df0420580c6f95c0a4ec325604dca32bee0a01d869367eda6073a49","source":{"kind":"arxiv","id":"2303.04761","version":1},"attestation_state":"computed","paper":{"title":"Video-P2P: Video Editing with Cross-attention Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaya Jia, Shaoteng Liu, Wenbo Li, Yuechen Zhang, Zhe Lin","submitted_at":"2023-03-08T17:53:49Z","abstract_excerpt":"This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control. While attention control has proven effective for image editing with pre-trained image generation models, there are currently no large-scale video generation models publicly available. Video-P2P addresses this limitation by adapting an image generation diffusion model to complete various video editing tasks. Specifically, we propose to first tune a Text-to-Set (T2S) model to complete an approximate inversion and then optimize a shared unconditional embedding to achieve accurate video inve"},"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":"2303.04761","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-08T17:53:49Z","cross_cats_sorted":[],"title_canon_sha256":"5614af44ca272c876064d5187d93311b75e761a235861f756e192191d9dec877","abstract_canon_sha256":"f62f6c4fc553d88824c7155c2aa2e042480ba900b5e34139198578694bfd4dc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:24.862771Z","signature_b64":"kpkLMDBRQpZftwcXn02HhbsZbh5ibJJAbgvNZG2ruwu4Jiv4N6kNSgtu8fPiQm2KcXYlC7+UjFoh05Nx4VbNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df5bcc46df0420580c6f95c0a4ec325604dca32bee0a01d869367eda6073a49","last_reissued_at":"2026-07-05T05:49:24.862265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:24.862265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-P2P: Video Editing with Cross-attention Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaya Jia, Shaoteng Liu, Wenbo Li, Yuechen Zhang, Zhe Lin","submitted_at":"2023-03-08T17:53:49Z","abstract_excerpt":"This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control. While attention control has proven effective for image editing with pre-trained image generation models, there are currently no large-scale video generation models publicly available. Video-P2P addresses this limitation by adapting an image generation diffusion model to complete various video editing tasks. Specifically, we propose to first tune a Text-to-Set (T2S) model to complete an approximate inversion and then optimize a shared unconditional embedding to achieve accurate video inve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04761","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/2303.04761/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":"2303.04761","created_at":"2026-07-05T05:49:24.862330+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04761v1","created_at":"2026-07-05T05:49:24.862330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04761","created_at":"2026-07-05T05:49:24.862330+00:00"},{"alias_kind":"pith_short_12","alias_value":"JX23ZRDN6BBA","created_at":"2026-07-05T05:49:24.862330+00:00"},{"alias_kind":"pith_short_16","alias_value":"JX23ZRDN6BBALAGG","created_at":"2026-07-05T05:49:24.862330+00:00"},{"alias_kind":"pith_short_8","alias_value":"JX23ZRDN","created_at":"2026-07-05T05:49:24.862330+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2307.10373","citing_title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05898","citing_title":"Physics-Aware Video Instance Removal Benchmark","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13841","citing_title":"DiffMagicFace: Identity Consistent Facial Editing of Real Videos","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV","json":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV.json","graph_json":"https://pith.science/api/pith-number/JX23ZRDN6BBALAGG7FOAUTWDEV/graph.json","events_json":"https://pith.science/api/pith-number/JX23ZRDN6BBALAGG7FOAUTWDEV/events.json","paper":"https://pith.science/paper/JX23ZRDN"},"agent_actions":{"view_html":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV","download_json":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV.json","view_paper":"https://pith.science/paper/JX23ZRDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04761&json=true","fetch_graph":"https://pith.science/api/pith-number/JX23ZRDN6BBALAGG7FOAUTWDEV/graph.json","fetch_events":"https://pith.science/api/pith-number/JX23ZRDN6BBALAGG7FOAUTWDEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV/action/storage_attestation","attest_author":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV/action/author_attestation","sign_citation":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV/action/citation_signature","submit_replication":"https://pith.science/pith/JX23ZRDN6BBALAGG7FOAUTWDEV/action/replication_record"}},"created_at":"2026-07-05T05:49:24.862330+00:00","updated_at":"2026-07-05T05:49:24.862330+00:00"}