{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MWW6KVJWSNXCSOESQUOORRCRFN","short_pith_number":"pith:MWW6KVJW","schema_version":"1.0","canonical_sha256":"65ade55536936e293892851ce8c4512b433382c9a983c8ea5caae0f415440426","source":{"kind":"arxiv","id":"2502.20323","version":5},"attestation_state":"computed","paper":{"title":"ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanqin Wang, Nabarun Goswami, Tatsuya Harada, Xuangeng Chu, Ziteng Cui","submitted_at":"2025-02-27T17:49:01Z","abstract_excerpt":"Speech-driven 3D facial animation aims to generate realistic lip movements and facial expressions for 3D head models from arbitrary audio clips. Although existing diffusion-based methods are capable of producing natural motions, their slow generation speed limits their application potential. In this paper, we introduce a novel autoregressive model that achieves real-time generation of highly synchronized lip movements and realistic head poses and eye blinks by learning a mapping from speech to a multi-scale motion codebook. Furthermore, our model can adapt to unseen speaking styles, enabling t"},"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":"2502.20323","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T17:49:01Z","cross_cats_sorted":[],"title_canon_sha256":"b3fbfdcc5d8e3fda54d486c8cb2cc58e20b91fbd11cd548b789b1b5bbf80387a","abstract_canon_sha256":"2d0d9b41a78023ea78c442d6e0382e620d0d5249b1417d91c90bec2ff2ded3a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:31.715041Z","signature_b64":"Nq4OOJQBZRTLA32UOf7dFpCZ6ho0TfJUv23rJsY3ZF2iKIiyngcCfZUSqAGd7xD0+t0R6OVr1XjNqSBa4DhoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ade55536936e293892851ce8c4512b433382c9a983c8ea5caae0f415440426","last_reissued_at":"2026-07-05T12:04:31.714530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:31.714530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanqin Wang, Nabarun Goswami, Tatsuya Harada, Xuangeng Chu, Ziteng Cui","submitted_at":"2025-02-27T17:49:01Z","abstract_excerpt":"Speech-driven 3D facial animation aims to generate realistic lip movements and facial expressions for 3D head models from arbitrary audio clips. Although existing diffusion-based methods are capable of producing natural motions, their slow generation speed limits their application potential. In this paper, we introduce a novel autoregressive model that achieves real-time generation of highly synchronized lip movements and realistic head poses and eye blinks by learning a mapping from speech to a multi-scale motion codebook. Furthermore, our model can adapt to unseen speaking styles, enabling t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20323","kind":"arxiv","version":5},"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/2502.20323/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":"2502.20323","created_at":"2026-07-05T12:04:31.714590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20323v5","created_at":"2026-07-05T12:04:31.714590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20323","created_at":"2026-07-05T12:04:31.714590+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWW6KVJWSNXC","created_at":"2026-07-05T12:04:31.714590+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWW6KVJWSNXCSOES","created_at":"2026-07-05T12:04:31.714590+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWW6KVJW","created_at":"2026-07-05T12:04:31.714590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.12052","citing_title":"FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17211","citing_title":"EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN","json":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN.json","graph_json":"https://pith.science/api/pith-number/MWW6KVJWSNXCSOESQUOORRCRFN/graph.json","events_json":"https://pith.science/api/pith-number/MWW6KVJWSNXCSOESQUOORRCRFN/events.json","paper":"https://pith.science/paper/MWW6KVJW"},"agent_actions":{"view_html":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN","download_json":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN.json","view_paper":"https://pith.science/paper/MWW6KVJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20323&json=true","fetch_graph":"https://pith.science/api/pith-number/MWW6KVJWSNXCSOESQUOORRCRFN/graph.json","fetch_events":"https://pith.science/api/pith-number/MWW6KVJWSNXCSOESQUOORRCRFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN/action/storage_attestation","attest_author":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN/action/author_attestation","sign_citation":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN/action/citation_signature","submit_replication":"https://pith.science/pith/MWW6KVJWSNXCSOESQUOORRCRFN/action/replication_record"}},"created_at":"2026-07-05T12:04:31.714590+00:00","updated_at":"2026-07-05T12:04:31.714590+00:00"}