{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BMJ2XVFXMK75ZK4OCFH72JUNO5","short_pith_number":"pith:BMJ2XVFX","schema_version":"1.0","canonical_sha256":"0b13abd4b762bfdcab8e114ffd268d774614da96a3668678d4171f3e1a29063a","source":{"kind":"arxiv","id":"2403.11568","version":2},"attestation_state":"computed","paper":{"title":"EffiVED:Efficient Video Editing via Text-instruction Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Qin, Weizhi Wang, Zhenghao Zhang, Zuozhuo Dai","submitted_at":"2024-03-18T08:42:08Z","abstract_excerpt":"Large-scale text-to-video models have shown remarkable abilities, but their direct application in video editing remains challenging due to limited available datasets. Current video editing methods commonly require per-video fine-tuning of diffusion models or specific inversion optimization to ensure high-fidelity edits. In this paper, we introduce EffiVED, an efficient diffusion-based model that directly supports instruction-guided video editing. To achieve this, we present two efficient workflows to gather video editing pairs, utilizing augmentation and fundamental vision-language techniques."},"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":"2403.11568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-18T08:42:08Z","cross_cats_sorted":[],"title_canon_sha256":"5a996bef8934528d4e831342a2d44a4821c227df93ef4cb4972bfa00a4b3d6a0","abstract_canon_sha256":"883e7de3774f5ef15d609abe913d551142e6ca23240e60403b946159b07a4f69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:25.486058Z","signature_b64":"QzPb/kkic2diHPzxosMxLgANn0LzSIfEsA1XLQDMAYr2AxNfYSnn04PEUEK1smvk5NjHnOyFJhLJtuTuTps/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b13abd4b762bfdcab8e114ffd268d774614da96a3668678d4171f3e1a29063a","last_reissued_at":"2026-07-05T08:27:25.485628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:25.485628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EffiVED:Efficient Video Editing via Text-instruction Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Qin, Weizhi Wang, Zhenghao Zhang, Zuozhuo Dai","submitted_at":"2024-03-18T08:42:08Z","abstract_excerpt":"Large-scale text-to-video models have shown remarkable abilities, but their direct application in video editing remains challenging due to limited available datasets. Current video editing methods commonly require per-video fine-tuning of diffusion models or specific inversion optimization to ensure high-fidelity edits. In this paper, we introduce EffiVED, an efficient diffusion-based model that directly supports instruction-guided video editing. To achieve this, we present two efficient workflows to gather video editing pairs, utilizing augmentation and fundamental vision-language techniques."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11568","kind":"arxiv","version":2},"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/2403.11568/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":"2403.11568","created_at":"2026-07-05T08:27:25.485687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11568v2","created_at":"2026-07-05T08:27:25.485687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11568","created_at":"2026-07-05T08:27:25.485687+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMJ2XVFXMK75","created_at":"2026-07-05T08:27:25.485687+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMJ2XVFXMK75ZK4O","created_at":"2026-07-05T08:27:25.485687+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMJ2XVFX","created_at":"2026-07-05T08:27:25.485687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23254","citing_title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24674","citing_title":"Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07154","citing_title":"PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":270,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5","json":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5.json","graph_json":"https://pith.science/api/pith-number/BMJ2XVFXMK75ZK4OCFH72JUNO5/graph.json","events_json":"https://pith.science/api/pith-number/BMJ2XVFXMK75ZK4OCFH72JUNO5/events.json","paper":"https://pith.science/paper/BMJ2XVFX"},"agent_actions":{"view_html":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5","download_json":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5.json","view_paper":"https://pith.science/paper/BMJ2XVFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11568&json=true","fetch_graph":"https://pith.science/api/pith-number/BMJ2XVFXMK75ZK4OCFH72JUNO5/graph.json","fetch_events":"https://pith.science/api/pith-number/BMJ2XVFXMK75ZK4OCFH72JUNO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5/action/storage_attestation","attest_author":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5/action/author_attestation","sign_citation":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5/action/citation_signature","submit_replication":"https://pith.science/pith/BMJ2XVFXMK75ZK4OCFH72JUNO5/action/replication_record"}},"created_at":"2026-07-05T08:27:25.485687+00:00","updated_at":"2026-07-05T08:27:25.485687+00:00"}