{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OQH35PAHPTUTYF7INFT4Y2MOBW","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":"2987a06dd2180d89deec31aac35f25a5e21bccf42f0b9bd0af07e3aae15d3757","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-25T12:49:06Z","title_canon_sha256":"71f14a04f133546fdd80e24fe66719094280c77753d071c9391b62328c0bf694"},"schema_version":"1.0","source":{"id":"2507.19225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19225","created_at":"2026-07-05T11:43:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19225v1","created_at":"2026-07-05T11:43:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19225","created_at":"2026-07-05T11:43:21Z"},{"alias_kind":"pith_short_12","alias_value":"OQH35PAHPTUT","created_at":"2026-07-05T11:43:21Z"},{"alias_kind":"pith_short_16","alias_value":"OQH35PAHPTUTYF7I","created_at":"2026-07-05T11:43:21Z"},{"alias_kind":"pith_short_8","alias_value":"OQH35PAH","created_at":"2026-07-05T11:43:21Z"}],"graph_snapshots":[{"event_id":"sha256:aa856712288fdce6e6b08c8a316db08087559c5467f23ec3a5a1a273686f8aa5","target":"graph","created_at":"2026-07-05T11:43:21Z","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/2507.19225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies in speech-driven talking face generation achieve promising results, but their reliance on fixed-driven speech limits further applications (e.g., face-voice mismatch). Thus, we extend the task to a more challenging setting: given a face image and text to speak, generating both talking face animation and its corresponding speeches. Accordingly, we propose a novel framework, Face2VoiceSync, with several novel contributions: 1) Voice-Face Alignment, ensuring generated voices match facial appearance; 2) Diversity \\& Manipulation, enabling generated voice control over paralinguistic f","authors_text":"Fang Kang, Haoyu Chen, Yin Cao","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-25T12:49:06Z","title":"Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19225","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":"sha256:5ab94c560fd4cf998badaac2046b5e99d55fbaa02315163b8f44d9d7cb8db911","target":"record","created_at":"2026-07-05T11:43:21Z","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":"2987a06dd2180d89deec31aac35f25a5e21bccf42f0b9bd0af07e3aae15d3757","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-25T12:49:06Z","title_canon_sha256":"71f14a04f133546fdd80e24fe66719094280c77753d071c9391b62328c0bf694"},"schema_version":"1.0","source":{"id":"2507.19225","kind":"arxiv","version":1}},"canonical_sha256":"740fbebc077ce93c17e86967cc698e0d86f0e6b3b05028904ea50ae34222188f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"740fbebc077ce93c17e86967cc698e0d86f0e6b3b05028904ea50ae34222188f","first_computed_at":"2026-07-05T11:43:21.744133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:21.744133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bWLKjpFb2xKlmL3SE4D2ewj28lFbexzLP8dudeQFB6naFGbu1KCsJBrKhsqoXENHjRGYNpO/MWpgZGZf68iIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:21.744588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ab94c560fd4cf998badaac2046b5e99d55fbaa02315163b8f44d9d7cb8db911","sha256:aa856712288fdce6e6b08c8a316db08087559c5467f23ec3a5a1a273686f8aa5"],"state_sha256":"f70d0681e3123be86b827aeadbeba14832b5a68cc17433d7a9bdc00af693aac1"}