{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:53YO36X6PJKBUJMOWZG4SBFG7F","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":"7e6fe7f872bf13e3d978075c72f03c37273af39ed1eacfb2c5b8b60ca141c433","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T22:02:30Z","title_canon_sha256":"9dde919755eaf6e4d5ee0180d75db7c4cd72762fe14c9e72274af4c047c5c488"},"schema_version":"1.0","source":{"id":"2410.07463","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07463","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07463v2","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07463","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"pith_short_12","alias_value":"53YO36X6PJKB","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"53YO36X6PJKBUJMO","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"53YO36X6","created_at":"2026-07-05T09:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:29a5680f64d82a20b7d8f9b3f475ea616c1c8f072914a4cc00bc661a4120975e","target":"graph","created_at":"2026-07-05T09:33:10Z","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/2410.07463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a novel task called language-guided joint audio-visual editing. Given an audio and image pair of a sounding event, this task aims at generating new audio-visual content by editing the given sounding event conditioned on the language guidance. For instance, we can alter the background environment of a sounding object while keeping its appearance unchanged, or we can add new sounds contextualized to the visual content. To address this task, we propose a new diffusion-based framework for joint audio-visual editing and introduce two key ideas. Firstly, we propose a one-","authors_text":"Anurag Kumar, Chao Huang, Chenliang Xu, Susan Liang, Yapeng Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T22:02:30Z","title":"Language-Guided Joint Audio-Visual Editing via One-Shot Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07463","kind":"arxiv","version":2},"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:b2008fd4fd249b80c0b6246aebd6b0725f08ea91be24bd68265e58aa1f2de8cc","target":"record","created_at":"2026-07-05T09:33:10Z","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":"7e6fe7f872bf13e3d978075c72f03c37273af39ed1eacfb2c5b8b60ca141c433","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T22:02:30Z","title_canon_sha256":"9dde919755eaf6e4d5ee0180d75db7c4cd72762fe14c9e72274af4c047c5c488"},"schema_version":"1.0","source":{"id":"2410.07463","kind":"arxiv","version":2}},"canonical_sha256":"eef0edfafe7a541a258eb64dc904a6f94393f2cb2e0653f4f64e682dd983155e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eef0edfafe7a541a258eb64dc904a6f94393f2cb2e0653f4f64e682dd983155e","first_computed_at":"2026-07-05T09:33:10.587563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:10.587563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X6r3YQtFeIMjsUoWRXGIt09I4N8AbN3dGkuBlJuId4WzF6oJxPlhjWc6lO12Qn/0EMVdQ0zbHoTS7ocYaP3MCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:10.588163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07463","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2008fd4fd249b80c0b6246aebd6b0725f08ea91be24bd68265e58aa1f2de8cc","sha256:29a5680f64d82a20b7d8f9b3f475ea616c1c8f072914a4cc00bc661a4120975e"],"state_sha256":"2247ef769da28f5fcafa859609e4baaf8dc73fc3e5056524f9fe140057a037b8"}