{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E25LKWZKGVIBRD26KAXCC4Q2WV","short_pith_number":"pith:E25LKWZK","schema_version":"1.0","canonical_sha256":"26bab55b2a3550188f5e502e21721ab54f2ef0f454cbcad68bbc30adbee499d5","source":{"kind":"arxiv","id":"2507.00498","version":3},"attestation_state":"computed","paper":{"title":"MuteSwap: Visual-informed Silent Video Identity Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Yifan Liu, Yu Fang, Zhouhan Lin","submitted_at":"2025-07-01T07:13:34Z","abstract_excerpt":"Conventional voice conversion modifies voice characteristics from a source speaker to a target speaker, relying on audio input from both sides. However, this process becomes infeasible when clean audio is unavailable, such as in silent videos or noisy environments. In this work, we focus on the task of Silent Face-based Voice Conversion (SFVC), which does voice conversion entirely from visual inputs. i.e., given images of a target speaker and a silent video of a source speaker containing lip motion, SFVC generates speech aligning the identity of the target speaker while preserving the speech c"},"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":"2507.00498","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-01T07:13:34Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"f68758fd72d9e32c300bedb3763c35a64ce893cd3af5b10285b40a89ef43e273","abstract_canon_sha256":"bd144287af9d69acf580ffcbc0fe9933e4a9e57cc5d4ccb04ed955fe486d556e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:25.352242Z","signature_b64":"iSNb0C4+fcI5/U1jGE4gq5jdyg0VVOxpWvfhyoWxRZX+KGsYc6h4Ocekt3kb+cm0YbPILHyKgNv6kC5DE0T2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26bab55b2a3550188f5e502e21721ab54f2ef0f454cbcad68bbc30adbee499d5","last_reissued_at":"2026-07-05T11:47:25.351678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:25.351678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuteSwap: Visual-informed Silent Video Identity Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Yifan Liu, Yu Fang, Zhouhan Lin","submitted_at":"2025-07-01T07:13:34Z","abstract_excerpt":"Conventional voice conversion modifies voice characteristics from a source speaker to a target speaker, relying on audio input from both sides. However, this process becomes infeasible when clean audio is unavailable, such as in silent videos or noisy environments. In this work, we focus on the task of Silent Face-based Voice Conversion (SFVC), which does voice conversion entirely from visual inputs. i.e., given images of a target speaker and a silent video of a source speaker containing lip motion, SFVC generates speech aligning the identity of the target speaker while preserving the speech c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00498","kind":"arxiv","version":3},"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/2507.00498/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":"2507.00498","created_at":"2026-07-05T11:47:25.351743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00498v3","created_at":"2026-07-05T11:47:25.351743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00498","created_at":"2026-07-05T11:47:25.351743+00:00"},{"alias_kind":"pith_short_12","alias_value":"E25LKWZKGVIB","created_at":"2026-07-05T11:47:25.351743+00:00"},{"alias_kind":"pith_short_16","alias_value":"E25LKWZKGVIBRD26","created_at":"2026-07-05T11:47:25.351743+00:00"},{"alias_kind":"pith_short_8","alias_value":"E25LKWZK","created_at":"2026-07-05T11:47:25.351743+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/E25LKWZKGVIBRD26KAXCC4Q2WV","json":"https://pith.science/pith/E25LKWZKGVIBRD26KAXCC4Q2WV.json","graph_json":"https://pith.science/api/pith-number/E25LKWZKGVIBRD26KAXCC4Q2WV/graph.json","events_json":"https://pith.science/api/pith-number/E25LKWZKGVIBRD26KAXCC4Q2WV/events.json","paper":"https://pith.science/paper/E25LKWZK"},"agent_actions":{"view_html":"https://pith.science/pith/E25LKWZKGVIBRD26KAXCC4Q2WV","download_json":"https://pith.science/pith/E25LKWZKGVIBRD26KAXCC4Q2WV.json","view_paper":"https://pith.science/paper/E25LKWZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00498&json=true","fetch_graph":"https://pith.science/api/pith-number/E25LKWZKGVIBRD26KAXCC4Q2WV/graph.json","fetch_events":"https://pith.science/api/pith-number/E25LKWZKGVIBRD26KAXCC4Q2WV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E25LKWZKGVIBRD26KAXCC4Q2WV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E25LKWZKGVIBRD26KAXCC4Q2WV/action/storage_attestation","attest_author":"https://pith.science/pith/E25LKWZKGVIBRD26KAXCC4Q2WV/action/author_attestation","sign_citation":"https://pith.science/pith/E25LKWZKGVIBRD26KAXCC4Q2WV/action/citation_signature","submit_replication":"https://pith.science/pith/E25LKWZKGVIBRD26KAXCC4Q2WV/action/replication_record"}},"created_at":"2026-07-05T11:47:25.351743+00:00","updated_at":"2026-07-05T11:47:25.351743+00:00"}