{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5M3JPRFG442GWJNQ5YR22ZYWQC","short_pith_number":"pith:5M3JPRFG","schema_version":"1.0","canonical_sha256":"eb3697c4a6e7346b25b0ee23ad67168099f3915830f5a9d28d58404d8c3cbc8e","source":{"kind":"arxiv","id":"2403.16111","version":1},"attestation_state":"computed","paper":{"title":"EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hehe Fan, Linchao Zhu, Xiangpeng Yang, Yi Yang","submitted_at":"2024-03-24T12:04:06Z","abstract_excerpt":"Current diffusion-based video editing primarily focuses on local editing (\\textit{e.g.,} object/background editing) or global style editing by utilizing various dense correspondences. However, these methods often fail to accurately edit the foreground and background simultaneously while preserving the original layout. We find that the crux of the issue stems from the imprecise distribution of attention weights across designated regions, including inaccurate text-to-attribute control and attention leakage. To tackle this issue, we introduce EVA, a \\textbf{zero-shot} and \\textbf{multi-attribute}"},"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":"2403.16111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-24T12:04:06Z","cross_cats_sorted":[],"title_canon_sha256":"9d1bd4a77249d04d26a87ece2cb865aab78f1a67d7d19c964cde534ee235f54b","abstract_canon_sha256":"cadfb00cf1c5538c501f23c9b6ff7b738df663d1f4c8ef62e41a57556b75348c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:10.716109Z","signature_b64":"B0hQ/oq2cjIQs0v0/vPIwDjHvGKHyIkhZCSVOa6VrKJlPB951iGfHpmWbak2gTc3iPxSsr73UECOmJQ7SJ3tBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb3697c4a6e7346b25b0ee23ad67168099f3915830f5a9d28d58404d8c3cbc8e","last_reissued_at":"2026-07-05T08:00:10.715633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:10.715633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hehe Fan, Linchao Zhu, Xiangpeng Yang, Yi Yang","submitted_at":"2024-03-24T12:04:06Z","abstract_excerpt":"Current diffusion-based video editing primarily focuses on local editing (\\textit{e.g.,} object/background editing) or global style editing by utilizing various dense correspondences. However, these methods often fail to accurately edit the foreground and background simultaneously while preserving the original layout. We find that the crux of the issue stems from the imprecise distribution of attention weights across designated regions, including inaccurate text-to-attribute control and attention leakage. To tackle this issue, we introduce EVA, a \\textbf{zero-shot} and \\textbf{multi-attribute}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16111","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/2403.16111/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":"2403.16111","created_at":"2026-07-05T08:00:10.715690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16111v1","created_at":"2026-07-05T08:00:10.715690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16111","created_at":"2026-07-05T08:00:10.715690+00:00"},{"alias_kind":"pith_short_12","alias_value":"5M3JPRFG442G","created_at":"2026-07-05T08:00:10.715690+00:00"},{"alias_kind":"pith_short_16","alias_value":"5M3JPRFG442GWJNQ","created_at":"2026-07-05T08:00:10.715690+00:00"},{"alias_kind":"pith_short_8","alias_value":"5M3JPRFG","created_at":"2026-07-05T08:00:10.715690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":258,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC","json":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC.json","graph_json":"https://pith.science/api/pith-number/5M3JPRFG442GWJNQ5YR22ZYWQC/graph.json","events_json":"https://pith.science/api/pith-number/5M3JPRFG442GWJNQ5YR22ZYWQC/events.json","paper":"https://pith.science/paper/5M3JPRFG"},"agent_actions":{"view_html":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC","download_json":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC.json","view_paper":"https://pith.science/paper/5M3JPRFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16111&json=true","fetch_graph":"https://pith.science/api/pith-number/5M3JPRFG442GWJNQ5YR22ZYWQC/graph.json","fetch_events":"https://pith.science/api/pith-number/5M3JPRFG442GWJNQ5YR22ZYWQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC/action/storage_attestation","attest_author":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC/action/author_attestation","sign_citation":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC/action/citation_signature","submit_replication":"https://pith.science/pith/5M3JPRFG442GWJNQ5YR22ZYWQC/action/replication_record"}},"created_at":"2026-07-05T08:00:10.715690+00:00","updated_at":"2026-07-05T08:00:10.715690+00:00"}