{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3EEY7HJGC7HZFPACZE2YLD6ICB","short_pith_number":"pith:3EEY7HJG","schema_version":"1.0","canonical_sha256":"d9098f9d2617cf92bc02c935858fc8104a614f8290ff7d99a3b862d8bb63659c","source":{"kind":"arxiv","id":"2503.20782","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Gedas Bertasius, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Xiaofei Wang, Yan-Bo Lin, Zhengyuan Yang","submitted_at":"2025-03-26T17:59:04Z","abstract_excerpt":"In this paper, we introduce zero-shot audio-video editing, a novel task that requires transforming original audio-visual content to align with a specified textual prompt without additional model training. To evaluate this task, we curate a benchmark dataset, AvED-Bench, designed explicitly for zero-shot audio-video editing. AvED-Bench includes 110 videos, each with a 10-second duration, spanning 11 categories from VGGSound. It offers diverse prompts and scenarios that require precise alignment between auditory and visual elements, enabling robust evaluation. We identify limitations in existing"},"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":"2503.20782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:04Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"0899093892cb6dffd91368056bda5a45f27f6efbf53b2e80e600ffa7a138aa71","abstract_canon_sha256":"c9eee457b1abb721a41855d6e3242f8c77a22603012d8fb11e15b57d2e8cd7f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:44.054688Z","signature_b64":"Q8dNYSZ1/lPgYYDAwvS9Znvc7P8zKRLKyrVAuPUrIW9/AMwJ70MEy3ZXbvA7EhEmmrgEofmcu2g9GcPMhaqiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9098f9d2617cf92bc02c935858fc8104a614f8290ff7d99a3b862d8bb63659c","last_reissued_at":"2026-07-05T10:39:44.054189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:44.054189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Gedas Bertasius, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Xiaofei Wang, Yan-Bo Lin, Zhengyuan Yang","submitted_at":"2025-03-26T17:59:04Z","abstract_excerpt":"In this paper, we introduce zero-shot audio-video editing, a novel task that requires transforming original audio-visual content to align with a specified textual prompt without additional model training. To evaluate this task, we curate a benchmark dataset, AvED-Bench, designed explicitly for zero-shot audio-video editing. AvED-Bench includes 110 videos, each with a 10-second duration, spanning 11 categories from VGGSound. It offers diverse prompts and scenarios that require precise alignment between auditory and visual elements, enabling robust evaluation. We identify limitations in existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20782","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/2503.20782/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":"2503.20782","created_at":"2026-07-05T10:39:44.054254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20782v1","created_at":"2026-07-05T10:39:44.054254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20782","created_at":"2026-07-05T10:39:44.054254+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EEY7HJGC7HZ","created_at":"2026-07-05T10:39:44.054254+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EEY7HJGC7HZFPAC","created_at":"2026-07-05T10:39:44.054254+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EEY7HJG","created_at":"2026-07-05T10:39:44.054254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03168","citing_title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10571","citing_title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB","json":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB.json","graph_json":"https://pith.science/api/pith-number/3EEY7HJGC7HZFPACZE2YLD6ICB/graph.json","events_json":"https://pith.science/api/pith-number/3EEY7HJGC7HZFPACZE2YLD6ICB/events.json","paper":"https://pith.science/paper/3EEY7HJG"},"agent_actions":{"view_html":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB","download_json":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB.json","view_paper":"https://pith.science/paper/3EEY7HJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20782&json=true","fetch_graph":"https://pith.science/api/pith-number/3EEY7HJGC7HZFPACZE2YLD6ICB/graph.json","fetch_events":"https://pith.science/api/pith-number/3EEY7HJGC7HZFPACZE2YLD6ICB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB/action/storage_attestation","attest_author":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB/action/author_attestation","sign_citation":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB/action/citation_signature","submit_replication":"https://pith.science/pith/3EEY7HJGC7HZFPACZE2YLD6ICB/action/replication_record"}},"created_at":"2026-07-05T10:39:44.054254+00:00","updated_at":"2026-07-05T10:39:44.054254+00:00"}