{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XUUTGXMM3TWNK3AXWLQT4B5CMH","short_pith_number":"pith:XUUTGXMM","schema_version":"1.0","canonical_sha256":"bd29335d8cdcecd56c17b2e13e07a261c825b8f6fb8bfe53342e7127933f1aae","source":{"kind":"arxiv","id":"2508.20379","version":1},"attestation_state":"computed","paper":{"title":"Audio-Guided Visual Editing with Complex Multi-Modal Prompts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chanhyuk Choi, Hyeonyu Kim, Seokhoon Jeong, Seonghee Han, Taehwan Kim","submitted_at":"2025-08-28T03:00:30Z","abstract_excerpt":"Visual editing with diffusion models has made significant progress but often struggles with complex scenarios that textual guidance alone could not adequately describe, highlighting the need for additional non-text editing prompts. In this work, we introduce a novel audio-guided visual editing framework that can handle complex editing tasks with multiple text and audio prompts without requiring additional training. Existing audio-guided visual editing methods often necessitate training on specific datasets to align audio with text, limiting their generalization to real-world situations. We lev"},"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":"2508.20379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T03:00:30Z","cross_cats_sorted":[],"title_canon_sha256":"216d92e6e790c6b0edff8351981f86e3718f46fa91a0c33e98ccd426a5adc022","abstract_canon_sha256":"3fa84e2b9b170db5c967ee224f6a19d138c6e6d38d2afd4015f1ab335c68e62d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:35.738060Z","signature_b64":"S9QvdFaunKhD5kYZFm6zL2OjpZkPfJPdlPXGJiuOo3QjL18YhI6bru/U64i0dHCE2OK+BS8yw7A/rmFkySDKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd29335d8cdcecd56c17b2e13e07a261c825b8f6fb8bfe53342e7127933f1aae","last_reissued_at":"2026-07-05T12:00:35.737531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:35.737531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Guided Visual Editing with Complex Multi-Modal Prompts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chanhyuk Choi, Hyeonyu Kim, Seokhoon Jeong, Seonghee Han, Taehwan Kim","submitted_at":"2025-08-28T03:00:30Z","abstract_excerpt":"Visual editing with diffusion models has made significant progress but often struggles with complex scenarios that textual guidance alone could not adequately describe, highlighting the need for additional non-text editing prompts. In this work, we introduce a novel audio-guided visual editing framework that can handle complex editing tasks with multiple text and audio prompts without requiring additional training. Existing audio-guided visual editing methods often necessitate training on specific datasets to align audio with text, limiting their generalization to real-world situations. We lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20379","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/2508.20379/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":"2508.20379","created_at":"2026-07-05T12:00:35.737593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20379v1","created_at":"2026-07-05T12:00:35.737593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20379","created_at":"2026-07-05T12:00:35.737593+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUUTGXMM3TWN","created_at":"2026-07-05T12:00:35.737593+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUUTGXMM3TWNK3AX","created_at":"2026-07-05T12:00:35.737593+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUUTGXMM","created_at":"2026-07-05T12:00:35.737593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH","json":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH.json","graph_json":"https://pith.science/api/pith-number/XUUTGXMM3TWNK3AXWLQT4B5CMH/graph.json","events_json":"https://pith.science/api/pith-number/XUUTGXMM3TWNK3AXWLQT4B5CMH/events.json","paper":"https://pith.science/paper/XUUTGXMM"},"agent_actions":{"view_html":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH","download_json":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH.json","view_paper":"https://pith.science/paper/XUUTGXMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20379&json=true","fetch_graph":"https://pith.science/api/pith-number/XUUTGXMM3TWNK3AXWLQT4B5CMH/graph.json","fetch_events":"https://pith.science/api/pith-number/XUUTGXMM3TWNK3AXWLQT4B5CMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH/action/storage_attestation","attest_author":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH/action/author_attestation","sign_citation":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH/action/citation_signature","submit_replication":"https://pith.science/pith/XUUTGXMM3TWNK3AXWLQT4B5CMH/action/replication_record"}},"created_at":"2026-07-05T12:00:35.737593+00:00","updated_at":"2026-07-05T12:00:35.737593+00:00"}