{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NB24LJIYPEKKVGYWH6EQYZFGXS","short_pith_number":"pith:NB24LJIY","schema_version":"1.0","canonical_sha256":"6875c5a5187914aa9b163f890c64a6bca2f7753ab40a220a020028f1fcdf63c0","source":{"kind":"arxiv","id":"2504.18810","version":1},"attestation_state":"computed","paper":{"title":"Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Ma, Fei Yu, Yi Bin, Yifan Xie, Ying He","submitted_at":"2025-04-26T05:45:38Z","abstract_excerpt":"Talking face video generation with arbitrary speech audio is a significant challenge within the realm of digital human technology. The previous studies have emphasized the significance of audio-lip synchronization and visual quality. Currently, limited attention has been given to the learning of visual uncertainty, which creates several issues in existing systems, including inconsistent visual quality and unreliable performance across different input conditions. To address the problem, we propose a Joint Uncertainty Learning Network (JULNet) for high-quality talking face video generation, whic"},"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":"2504.18810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-26T05:45:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"937b25b1268b9019501d2d9ae648d51b73ee0cbeacd460afe21f01716dcee5e2","abstract_canon_sha256":"5e9978dfeb9a90458717a49874ff4fdc63db56f47f132a27b07883ed7bf4ffd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:21.781103Z","signature_b64":"8Dqj05x+M5bHzYdrLG67/Ad3D15iRu/86fo5tOAiASRXMaWtNJ+S74LOPGCVFajb+IgD9Kh6cL3TyV+zywlrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6875c5a5187914aa9b163f890c64a6bca2f7753ab40a220a020028f1fcdf63c0","last_reissued_at":"2026-07-05T10:54:21.780640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:21.780640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Ma, Fei Yu, Yi Bin, Yifan Xie, Ying He","submitted_at":"2025-04-26T05:45:38Z","abstract_excerpt":"Talking face video generation with arbitrary speech audio is a significant challenge within the realm of digital human technology. The previous studies have emphasized the significance of audio-lip synchronization and visual quality. Currently, limited attention has been given to the learning of visual uncertainty, which creates several issues in existing systems, including inconsistent visual quality and unreliable performance across different input conditions. To address the problem, we propose a Joint Uncertainty Learning Network (JULNet) for high-quality talking face video generation, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18810","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/2504.18810/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":"2504.18810","created_at":"2026-07-05T10:54:21.780691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18810v1","created_at":"2026-07-05T10:54:21.780691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18810","created_at":"2026-07-05T10:54:21.780691+00:00"},{"alias_kind":"pith_short_12","alias_value":"NB24LJIYPEKK","created_at":"2026-07-05T10:54:21.780691+00:00"},{"alias_kind":"pith_short_16","alias_value":"NB24LJIYPEKKVGYW","created_at":"2026-07-05T10:54:21.780691+00:00"},{"alias_kind":"pith_short_8","alias_value":"NB24LJIY","created_at":"2026-07-05T10:54:21.780691+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/NB24LJIYPEKKVGYWH6EQYZFGXS","json":"https://pith.science/pith/NB24LJIYPEKKVGYWH6EQYZFGXS.json","graph_json":"https://pith.science/api/pith-number/NB24LJIYPEKKVGYWH6EQYZFGXS/graph.json","events_json":"https://pith.science/api/pith-number/NB24LJIYPEKKVGYWH6EQYZFGXS/events.json","paper":"https://pith.science/paper/NB24LJIY"},"agent_actions":{"view_html":"https://pith.science/pith/NB24LJIYPEKKVGYWH6EQYZFGXS","download_json":"https://pith.science/pith/NB24LJIYPEKKVGYWH6EQYZFGXS.json","view_paper":"https://pith.science/paper/NB24LJIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18810&json=true","fetch_graph":"https://pith.science/api/pith-number/NB24LJIYPEKKVGYWH6EQYZFGXS/graph.json","fetch_events":"https://pith.science/api/pith-number/NB24LJIYPEKKVGYWH6EQYZFGXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NB24LJIYPEKKVGYWH6EQYZFGXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NB24LJIYPEKKVGYWH6EQYZFGXS/action/storage_attestation","attest_author":"https://pith.science/pith/NB24LJIYPEKKVGYWH6EQYZFGXS/action/author_attestation","sign_citation":"https://pith.science/pith/NB24LJIYPEKKVGYWH6EQYZFGXS/action/citation_signature","submit_replication":"https://pith.science/pith/NB24LJIYPEKKVGYWH6EQYZFGXS/action/replication_record"}},"created_at":"2026-07-05T10:54:21.780691+00:00","updated_at":"2026-07-05T10:54:21.780691+00:00"}