{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GW25QDOT3XUTGJKWQUHVU7K3XY","short_pith_number":"pith:GW25QDOT","schema_version":"1.0","canonical_sha256":"35b5d80dd3dde9332556850f5a7d5bbe2d99c5b53d109fd954cd6b70b74f6a11","source":{"kind":"arxiv","id":"2507.12723","version":1},"attestation_state":"computed","paper":{"title":"Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Minyoung Kim, Paul Hongsuck Seo, Sehwan Park, Sungmin Cha","submitted_at":"2025-07-17T02:02:39Z","abstract_excerpt":"Recent advances in voice cloning and lip synchronization models have enabled Synthesized Audiovisual Forgeries (SAVFs), where both audio and visuals are manipulated to mimic a target speaker. This significantly increases the risk of misinformation by making fake content seem real. To address this issue, existing methods detect or localize manipulations but cannot recover the authentic audio that conveys the semantic content of the message. This limitation reduces their effectiveness in combating audiovisual misinformation. In this work, we introduce the task of Authentic Audio Recovery (AAR) a"},"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":"2507.12723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-17T02:02:39Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"fe2f44d6a5e2c9ba1b9886dc2716464f9ea8b2ad396f17b6afa9576141d0e325","abstract_canon_sha256":"29261d9e6b15138c52211e1aacd75b50ad3a39f0e3e2c9c907b3d4f106014780"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:37.881172Z","signature_b64":"Y749nHvco8kuo/FIqKfaGq7BZeGBqnVS4jjB8rY03fwcum3r03RAz3u3XLE1Lozkqa3Y/gTzSFDkMcaVHmSKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35b5d80dd3dde9332556850f5a7d5bbe2d99c5b53d109fd954cd6b70b74f6a11","last_reissued_at":"2026-07-05T11:38:37.880597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:37.880597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Minyoung Kim, Paul Hongsuck Seo, Sehwan Park, Sungmin Cha","submitted_at":"2025-07-17T02:02:39Z","abstract_excerpt":"Recent advances in voice cloning and lip synchronization models have enabled Synthesized Audiovisual Forgeries (SAVFs), where both audio and visuals are manipulated to mimic a target speaker. This significantly increases the risk of misinformation by making fake content seem real. To address this issue, existing methods detect or localize manipulations but cannot recover the authentic audio that conveys the semantic content of the message. This limitation reduces their effectiveness in combating audiovisual misinformation. In this work, we introduce the task of Authentic Audio Recovery (AAR) a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12723","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/2507.12723/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":"2507.12723","created_at":"2026-07-05T11:38:37.880658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12723v1","created_at":"2026-07-05T11:38:37.880658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12723","created_at":"2026-07-05T11:38:37.880658+00:00"},{"alias_kind":"pith_short_12","alias_value":"GW25QDOT3XUT","created_at":"2026-07-05T11:38:37.880658+00:00"},{"alias_kind":"pith_short_16","alias_value":"GW25QDOT3XUTGJKW","created_at":"2026-07-05T11:38:37.880658+00:00"},{"alias_kind":"pith_short_8","alias_value":"GW25QDOT","created_at":"2026-07-05T11:38:37.880658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12723","citing_title":"Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY","json":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY.json","graph_json":"https://pith.science/api/pith-number/GW25QDOT3XUTGJKWQUHVU7K3XY/graph.json","events_json":"https://pith.science/api/pith-number/GW25QDOT3XUTGJKWQUHVU7K3XY/events.json","paper":"https://pith.science/paper/GW25QDOT"},"agent_actions":{"view_html":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY","download_json":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY.json","view_paper":"https://pith.science/paper/GW25QDOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12723&json=true","fetch_graph":"https://pith.science/api/pith-number/GW25QDOT3XUTGJKWQUHVU7K3XY/graph.json","fetch_events":"https://pith.science/api/pith-number/GW25QDOT3XUTGJKWQUHVU7K3XY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY/action/storage_attestation","attest_author":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY/action/author_attestation","sign_citation":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY/action/citation_signature","submit_replication":"https://pith.science/pith/GW25QDOT3XUTGJKWQUHVU7K3XY/action/replication_record"}},"created_at":"2026-07-05T11:38:37.880658+00:00","updated_at":"2026-07-05T11:38:37.880658+00:00"}