{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TKV7EFL52JNCJWT4DLIEPBJNFR","short_pith_number":"pith:TKV7EFL5","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"},"canonical_sha256":"9aabf2157dd25a24da7c1ad047852d2c7cf3563b90a324a552805f64baa20201","source":{"kind":"arxiv","id":"2301.06690","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.06690","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"arxiv_version","alias_value":"2301.06690v1","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06690","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"pith_short_12","alias_value":"TKV7EFL52JNC","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"pith_short_16","alias_value":"TKV7EFL52JNCJWT4","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"pith_short_8","alias_value":"TKV7EFL5","created_at":"2026-07-05T05:33:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TKV7EFL52JNCJWT4DLIEPBJNFR","target":"record","payload":{"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"},"canonical_sha256":"9aabf2157dd25a24da7c1ad047852d2c7cf3563b90a324a552805f64baa20201","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"},"source_kind":"arxiv","source_id":"2301.06690","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:33:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rZyZ3VL4WmQoG/2+OjQh2r60E8vkEOBoAZobHHwrGdpWOxZONxZ0VZf+eY6XjqCRZxN0vS19JrpVTIVLfZeOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:34:16.937505Z"},"content_sha256":"134108896d0969fa8bf141a3aa52492ce0f1552c1423259852734f234302fbb0","schema_version":"1.0","event_id":"sha256:134108896d0969fa8bf141a3aa52492ce0f1552c1423259852734f234302fbb0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TKV7EFL52JNCJWT4DLIEPBJNFR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:33:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/UrBht3U6eqTb7pPGRDF+sED5z77Tc2fdxpw9VyecASKJgRbR9noLTsrmYNFYmZxJloL4ifgjVA+lGDGKMmgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:34:16.987952Z"},"content_sha256":"127b16614eb016770eeb0e988731fca2ff5be18c1dd881edc4ca83246fa35643","schema_version":"1.0","event_id":"sha256:127b16614eb016770eeb0e988731fca2ff5be18c1dd881edc4ca83246fa35643"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/bundle.json","state_url":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T17:34:17Z","links":{"resolver":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR","bundle":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/bundle.json","state":"https://pith.science/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TKV7EFL52JNCJWT4DLIEPBJNFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TKV7EFL52JNCJWT4DLIEPBJNFR","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":"a666c7f56428696674f85f78e2f35d421625ef58ec45045aac25e2e30accac5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-17T04:09:58Z","title_canon_sha256":"a241a9083bb3bed854b384f4032400105a78d5274dbed80e2bbfb107bd55b655"},"schema_version":"1.0","source":{"id":"2301.06690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.06690","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"arxiv_version","alias_value":"2301.06690v1","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06690","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"pith_short_12","alias_value":"TKV7EFL52JNC","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"pith_short_16","alias_value":"TKV7EFL52JNCJWT4","created_at":"2026-07-05T05:33:34Z"},{"alias_kind":"pith_short_8","alias_value":"TKV7EFL5","created_at":"2026-07-05T05:33:34Z"}],"graph_snapshots":[{"event_id":"sha256:127b16614eb016770eeb0e988731fca2ff5be18c1dd881edc4ca83246fa35643","target":"graph","created_at":"2026-07-05T05:33:34Z","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/2301.06690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Di Kang, Jing Li, Linchao Bao, Wenjie Pei, Xuefei Zhe, Ying Zhang, Zhenyu He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-17T04:09:58Z","title":"Audio2Gestures: Generating Diverse Gestures from Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06690","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":"sha256:134108896d0969fa8bf141a3aa52492ce0f1552c1423259852734f234302fbb0","target":"record","created_at":"2026-07-05T05:33:34Z","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":"a666c7f56428696674f85f78e2f35d421625ef58ec45045aac25e2e30accac5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-17T04:09:58Z","title_canon_sha256":"a241a9083bb3bed854b384f4032400105a78d5274dbed80e2bbfb107bd55b655"},"schema_version":"1.0","source":{"id":"2301.06690","kind":"arxiv","version":1}},"canonical_sha256":"9aabf2157dd25a24da7c1ad047852d2c7cf3563b90a324a552805f64baa20201","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9aabf2157dd25a24da7c1ad047852d2c7cf3563b90a324a552805f64baa20201","first_computed_at":"2026-07-05T05:33:34.724885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:33:34.724885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dZR4/QzGav+ms1LclzmcYz/zMFHK8VrgYAeRZp+JtiVViSofSOXtZdyTHdVP5X9rticmgT4SL881JO6Tuv0mBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:33:34.725296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.06690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:134108896d0969fa8bf141a3aa52492ce0f1552c1423259852734f234302fbb0","sha256:127b16614eb016770eeb0e988731fca2ff5be18c1dd881edc4ca83246fa35643"],"state_sha256":"d71d1069b343f815daa0f9476d53556a077276983bf6b60267ffcd04d78ed73a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/bECDbDgiVPGC5ETUn9sIDrKX5w6l79ouJNjQDKEXUujBZubvJI/EX/PdwjwQxGC8fPrIXw7UDrYvYD1xcj8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:34:17.126202Z","bundle_sha256":"b1bc47470cdad661db28ba11d680412895db5c9dc0bfa8f4e5f8e64b7cf504bb"}}