{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TVLHT3D2K7B362F6QVQIUFFSWF","short_pith_number":"pith:TVLHT3D2","schema_version":"1.0","canonical_sha256":"9d5679ec7a57c3bf68be85608a14b2b151cc9be3902addad7eb1b61699491167","source":{"kind":"arxiv","id":"2404.10667","version":2},"attestation_state":"computed","paper":{"title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Chong Li, Guojun Chen, Jiaolong Yang, Sicheng Xu, Xin Tong, Yizhong Zhang, Yu-Xiao Guo, Zhenyu Zang","submitted_at":"2024-04-16T15:43:22Z","abstract_excerpt":"We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip. Our premiere model, VASA-1, is capable of not only generating lip movements that are exquisitely synchronized with the audio, but also producing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness. The core innovations include a holistic facial dynamics and head movement generation model that works in a face latent space, and the development of such an expre"},"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":"2404.10667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T15:43:22Z","cross_cats_sorted":[],"title_canon_sha256":"45f4a9b8c2b83ac4c4dd668afb69d082ec705e4dda490dc1ae1d753e026561a6","abstract_canon_sha256":"3073cde3622f02246e345ab89c161810abd6bc37f918cdd12450d415b254a595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:49.142539Z","signature_b64":"s3fTvq4v9pH820+3Dn3uGQQfByH4kjVE8tevprfNe6t6nos7j4Ku6SxtOHt3TZ6pevSi/y30PrHerSY3vOgqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d5679ec7a57c3bf68be85608a14b2b151cc9be3902addad7eb1b61699491167","last_reissued_at":"2026-07-05T09:28:49.142029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:49.142029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Chong Li, Guojun Chen, Jiaolong Yang, Sicheng Xu, Xin Tong, Yizhong Zhang, Yu-Xiao Guo, Zhenyu Zang","submitted_at":"2024-04-16T15:43:22Z","abstract_excerpt":"We introduce VASA, a framework for generating lifelike talking faces with appealing visual affective skills (VAS) given a single static image and a speech audio clip. Our premiere model, VASA-1, is capable of not only generating lip movements that are exquisitely synchronized with the audio, but also producing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness. The core innovations include a holistic facial dynamics and head movement generation model that works in a face latent space, and the development of such an expre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10667","kind":"arxiv","version":2},"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/2404.10667/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":"2404.10667","created_at":"2026-07-05T09:28:49.142090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10667v2","created_at":"2026-07-05T09:28:49.142090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10667","created_at":"2026-07-05T09:28:49.142090+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVLHT3D2K7B3","created_at":"2026-07-05T09:28:49.142090+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVLHT3D2K7B362F6","created_at":"2026-07-05T09:28:49.142090+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVLHT3D2","created_at":"2026-07-05T09:28:49.142090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25041","citing_title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25041","citing_title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25041","citing_title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2411.16748","citing_title":"Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2411.09209","citing_title":"JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03603","citing_title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23632","citing_title":"Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF","json":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF.json","graph_json":"https://pith.science/api/pith-number/TVLHT3D2K7B362F6QVQIUFFSWF/graph.json","events_json":"https://pith.science/api/pith-number/TVLHT3D2K7B362F6QVQIUFFSWF/events.json","paper":"https://pith.science/paper/TVLHT3D2"},"agent_actions":{"view_html":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF","download_json":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF.json","view_paper":"https://pith.science/paper/TVLHT3D2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10667&json=true","fetch_graph":"https://pith.science/api/pith-number/TVLHT3D2K7B362F6QVQIUFFSWF/graph.json","fetch_events":"https://pith.science/api/pith-number/TVLHT3D2K7B362F6QVQIUFFSWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF/action/storage_attestation","attest_author":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF/action/author_attestation","sign_citation":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF/action/citation_signature","submit_replication":"https://pith.science/pith/TVLHT3D2K7B362F6QVQIUFFSWF/action/replication_record"}},"created_at":"2026-07-05T09:28:49.142090+00:00","updated_at":"2026-07-05T09:28:49.142090+00:00"}