{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DFBWETJFZZNY5RZA5HPR3Z2GJM","short_pith_number":"pith:DFBWETJF","schema_version":"1.0","canonical_sha256":"1943624d25ce5b8ec720e9df1de7464b087f388a393e4ce9c20c5a94088f0867","source":{"kind":"arxiv","id":"2404.00368","version":2},"attestation_state":"computed","paper":{"title":"Towards Variable and Coordinated Holistic Co-Speech Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Huaiguang Jiang, Qiong Cao, Yandong Wen, Yifei Liu","submitted_at":"2024-03-30T13:41:57Z","abstract_excerpt":"This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination. Variability allows the avatar to exhibit a wide range of motions even with similar speech content, while coordination ensures a harmonious alignment among facial expressions, hand gestures, and body poses. We aim to achieve both with ProbTalk, a unified probabilistic framework designed to jointly model facial, hand, and body movements in speech. ProbTalk builds on the variational autoencoder (VAE) architecture and incorporates three core "},"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":"2404.00368","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T13:41:57Z","cross_cats_sorted":[],"title_canon_sha256":"d3a794615f4a1740009be81846541f5e419590d4cc0c46839429eac8611c7b71","abstract_canon_sha256":"57cae69bc94cf1c074de73690b03a80db54b5911217e7852fff9b1fb94151164"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:03.123389Z","signature_b64":"aq2MYdhtzh+jIV2BLZG6OnzlkvDX1BiBLmbWxYf7mNNnG9sif0vrSzf2g5HQUDwXisb6R3uvjL/VU163qW/4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1943624d25ce5b8ec720e9df1de7464b087f388a393e4ce9c20c5a94088f0867","last_reissued_at":"2026-07-05T08:08:03.122923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:03.122923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Variable and Coordinated Holistic Co-Speech Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Huaiguang Jiang, Qiong Cao, Yandong Wen, Yifei Liu","submitted_at":"2024-03-30T13:41:57Z","abstract_excerpt":"This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination. Variability allows the avatar to exhibit a wide range of motions even with similar speech content, while coordination ensures a harmonious alignment among facial expressions, hand gestures, and body poses. We aim to achieve both with ProbTalk, a unified probabilistic framework designed to jointly model facial, hand, and body movements in speech. ProbTalk builds on the variational autoencoder (VAE) architecture and incorporates three core "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00368","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/2404.00368/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":"2404.00368","created_at":"2026-07-05T08:08:03.122977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00368v2","created_at":"2026-07-05T08:08:03.122977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00368","created_at":"2026-07-05T08:08:03.122977+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFBWETJFZZNY","created_at":"2026-07-05T08:08:03.122977+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFBWETJFZZNY5RZA","created_at":"2026-07-05T08:08:03.122977+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFBWETJF","created_at":"2026-07-05T08:08:03.122977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10927","citing_title":"LiveGesture Streamable Co-Speech Gesture Generation Model","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM","json":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM.json","graph_json":"https://pith.science/api/pith-number/DFBWETJFZZNY5RZA5HPR3Z2GJM/graph.json","events_json":"https://pith.science/api/pith-number/DFBWETJFZZNY5RZA5HPR3Z2GJM/events.json","paper":"https://pith.science/paper/DFBWETJF"},"agent_actions":{"view_html":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM","download_json":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM.json","view_paper":"https://pith.science/paper/DFBWETJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00368&json=true","fetch_graph":"https://pith.science/api/pith-number/DFBWETJFZZNY5RZA5HPR3Z2GJM/graph.json","fetch_events":"https://pith.science/api/pith-number/DFBWETJFZZNY5RZA5HPR3Z2GJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM/action/storage_attestation","attest_author":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM/action/author_attestation","sign_citation":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM/action/citation_signature","submit_replication":"https://pith.science/pith/DFBWETJFZZNY5RZA5HPR3Z2GJM/action/replication_record"}},"created_at":"2026-07-05T08:08:03.122977+00:00","updated_at":"2026-07-05T08:08:03.122977+00:00"}