{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TKV7EFL52JNCJWT4DLIEPBJNFR","short_pith_number":"pith:TKV7EFL5","schema_version":"1.0","canonical_sha256":"9aabf2157dd25a24da7c1ad047852d2c7cf3563b90a324a552805f64baa20201","source":{"kind":"arxiv","id":"2301.06690","version":1},"attestation_state":"computed","paper":{"title":"Audio2Gestures: Generating Diverse Gestures from Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Kang, Jing Li, Linchao Bao, Wenjie Pei, Xuefei Zhe, Ying Zhang, Zhenyu He","submitted_at":"2023-01-17T04:09:58Z","abstract_excerpt":"People may perform diverse gestures affected by various mental and physical factors when speaking the same sentences. This inherent one-to-many relationship makes co-speech gesture generation from audio particularly challenging. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, easily resulting in plain/boring motions during inference. So we propose to explicitly model the one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code. The shared code is expected to be r"},"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":"2301.06690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-17T04:09:58Z","cross_cats_sorted":[],"title_canon_sha256":"a241a9083bb3bed854b384f4032400105a78d5274dbed80e2bbfb107bd55b655","abstract_canon_sha256":"a666c7f56428696674f85f78e2f35d421625ef58ec45045aac25e2e30accac5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:34.725296Z","signature_b64":"dZR4/QzGav+ms1LclzmcYz/zMFHK8VrgYAeRZp+JtiVViSofSOXtZdyTHdVP5X9rticmgT4SL881JO6Tuv0mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aabf2157dd25a24da7c1ad047852d2c7cf3563b90a324a552805f64baa20201","last_reissued_at":"2026-07-05T05:33:34.724885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:34.724885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio2Gestures: Generating Diverse Gestures from Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Kang, Jing Li, Linchao Bao, Wenjie Pei, Xuefei Zhe, Ying Zhang, Zhenyu He","submitted_at":"2023-01-17T04:09:58Z","abstract_excerpt":"People may perform diverse gestures affected by various mental and physical factors when speaking the same sentences. This inherent one-to-many relationship makes co-speech gesture generation from audio particularly challenging. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, easily resulting in plain/boring motions during inference. So we propose to explicitly model the one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code. The shared code is expected to be r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06690","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/2301.06690/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":"2301.06690","created_at":"2026-07-05T05:33:34.724950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06690v1","created_at":"2026-07-05T05:33:34.724950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06690","created_at":"2026-07-05T05:33:34.724950+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKV7EFL52JNC","created_at":"2026-07-05T05:33:34.724950+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKV7EFL52JNCJWT4","created_at":"2026-07-05T05:33:34.724950+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKV7EFL5","created_at":"2026-07-05T05:33:34.724950+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/TKV7EFL52JNCJWT4DLIEPBJNFR","json":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR.json","graph_json":"https://pith.science/api/pith-number/TKV7EFL52JNCJWT4DLIEPBJNFR/graph.json","events_json":"https://pith.science/api/pith-number/TKV7EFL52JNCJWT4DLIEPBJNFR/events.json","paper":"https://pith.science/paper/TKV7EFL5"},"agent_actions":{"view_html":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR","download_json":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR.json","view_paper":"https://pith.science/paper/TKV7EFL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06690&json=true","fetch_graph":"https://pith.science/api/pith-number/TKV7EFL52JNCJWT4DLIEPBJNFR/graph.json","fetch_events":"https://pith.science/api/pith-number/TKV7EFL52JNCJWT4DLIEPBJNFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/action/storage_attestation","attest_author":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/action/author_attestation","sign_citation":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/action/citation_signature","submit_replication":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/action/replication_record"}},"created_at":"2026-07-05T05:33:34.724950+00:00","updated_at":"2026-07-05T05:33:34.724950+00:00"}