{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3EEY7HJGC7HZFPACZE2YLD6ICB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c9eee457b1abb721a41855d6e3242f8c77a22603012d8fb11e15b57d2e8cd7f8","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:04Z","title_canon_sha256":"0899093892cb6dffd91368056bda5a45f27f6efbf53b2e80e600ffa7a138aa71"},"schema_version":"1.0","source":{"id":"2503.20782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.20782","created_at":"2026-07-05T10:39:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.20782v1","created_at":"2026-07-05T10:39:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20782","created_at":"2026-07-05T10:39:44Z"},{"alias_kind":"pith_short_12","alias_value":"3EEY7HJGC7HZ","created_at":"2026-07-05T10:39:44Z"},{"alias_kind":"pith_short_16","alias_value":"3EEY7HJGC7HZFPAC","created_at":"2026-07-05T10:39:44Z"},{"alias_kind":"pith_short_8","alias_value":"3EEY7HJG","created_at":"2026-07-05T10:39:44Z"}],"graph_snapshots":[{"event_id":"sha256:b4400300b8dbad17c69d16cae6ab930438b065223eeef3275183487c4320f166","target":"graph","created_at":"2026-07-05T10:39:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.20782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chung-Ching Lin, Gedas Bertasius, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Xiaofei Wang, Yan-Bo Lin, Zhengyuan Yang","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:04Z","title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20782","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bff1c7288fbcb8e95a072be8a1076ff694fb89090548b68e0b68c716e1976831","target":"record","created_at":"2026-07-05T10:39:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c9eee457b1abb721a41855d6e3242f8c77a22603012d8fb11e15b57d2e8cd7f8","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:04Z","title_canon_sha256":"0899093892cb6dffd91368056bda5a45f27f6efbf53b2e80e600ffa7a138aa71"},"schema_version":"1.0","source":{"id":"2503.20782","kind":"arxiv","version":1}},"canonical_sha256":"d9098f9d2617cf92bc02c935858fc8104a614f8290ff7d99a3b862d8bb63659c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9098f9d2617cf92bc02c935858fc8104a614f8290ff7d99a3b862d8bb63659c","first_computed_at":"2026-07-05T10:39:44.054189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:44.054189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q8dNYSZ1/lPgYYDAwvS9Znvc7P8zKRLKyrVAuPUrIW9/AMwJ70MEy3ZXbvA7EhEmmrgEofmcu2g9GcPMhaqiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:44.054688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.20782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bff1c7288fbcb8e95a072be8a1076ff694fb89090548b68e0b68c716e1976831","sha256:b4400300b8dbad17c69d16cae6ab930438b065223eeef3275183487c4320f166"],"state_sha256":"3c035a233824cb78259dcbb1b828b1da80c5c8dfb134b51d5053a44942b70c29"}