{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:C2GEQJ2HISDXXBLGOR3LBIRIX4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c15d9ef0b3f58b6ae6e2bd3ffb86dfc851d2e19985b169339c6691d51ecfa3d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-15T11:15:51Z","title_canon_sha256":"ed78b1ff16e6883022c2512ae725271d8b237b6070b444d389cbed96dabd1c4d"},"schema_version":"1.0","source":{"id":"2108.06720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.06720","created_at":"2026-07-05T03:05:57Z"},{"alias_kind":"arxiv_version","alias_value":"2108.06720v1","created_at":"2026-07-05T03:05:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.06720","created_at":"2026-07-05T03:05:57Z"},{"alias_kind":"pith_short_12","alias_value":"C2GEQJ2HISDX","created_at":"2026-07-05T03:05:57Z"},{"alias_kind":"pith_short_16","alias_value":"C2GEQJ2HISDXXBLG","created_at":"2026-07-05T03:05:57Z"},{"alias_kind":"pith_short_8","alias_value":"C2GEQJ2H","created_at":"2026-07-05T03:05:57Z"}],"graph_snapshots":[{"event_id":"sha256:786c2655d2acbd2045ee89c7ccef54b95fc2f5f7b89c34c7efaaf78f5ecd9570","target":"graph","created_at":"2026-07-05T03:05:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.06720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating conversational gestures from speech audio is challenging due to the inherent one-to-many mapping between audio and body motions. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, resulting in plain/boring motions during inference. In order to overcome this problem, we propose a novel conditional variational autoencoder (VAE) that explicitly models one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code. The shared code mainly models the strong correlati","authors_text":"Di Kang, Jing Li, Linchao Bao, Wenjie Pei, Xuefei Zhe, Ying Zhang, Zhenyu He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-15T11:15:51Z","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.06720","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc85c2cf5527bc0e0ddee7fe4839fc666afb1ede20b267cfe11c2b0cc328e135","target":"record","created_at":"2026-07-05T03:05:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c15d9ef0b3f58b6ae6e2bd3ffb86dfc851d2e19985b169339c6691d51ecfa3d3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-15T11:15:51Z","title_canon_sha256":"ed78b1ff16e6883022c2512ae725271d8b237b6070b444d389cbed96dabd1c4d"},"schema_version":"1.0","source":{"id":"2108.06720","kind":"arxiv","version":1}},"canonical_sha256":"168c48274744877b85667476b0a228bf0c5a331edd4f51bacdf40cf7fb64c440","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"168c48274744877b85667476b0a228bf0c5a331edd4f51bacdf40cf7fb64c440","first_computed_at":"2026-07-05T03:05:57.273795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:57.273795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OOOSV/TdFlMbUqqLaC9UeZiKdVFXcYWqC7XvezNFH12PJx9rfznu/TwNko4ltC5ETSg4eY0vsTPvxa8wPSgIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:57.274129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.06720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc85c2cf5527bc0e0ddee7fe4839fc666afb1ede20b267cfe11c2b0cc328e135","sha256:786c2655d2acbd2045ee89c7ccef54b95fc2f5f7b89c34c7efaaf78f5ecd9570"],"state_sha256":"cdac66e0395841a3bc9c56689ca30d8372885a292e30b1730c3dbfbb9eff35cb"}