{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IMUMMJFFMN45XPHUEE7M3Z4XZC","short_pith_number":"pith:IMUMMJFF","schema_version":"1.0","canonical_sha256":"4328c624a56379dbbcf4213ecde797c89a10808db6051997839627c3b5ba1daf","source":{"kind":"arxiv","id":"2501.18898","version":3},"attestation_state":"computed","paper":{"title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Haiyang Liu, Junhua Huang, Luchuan Song, Pinxin Liu","submitted_at":"2025-01-31T05:34:59Z","abstract_excerpt":"Generating full-body human gestures based on speech signals remains challenges on quality and speed. Existing approaches model different body regions such as body, legs and hands separately, which fail to capture the spatial interactions between them and result in unnatural and disjointed movements. Additionally, their autoregressive/diffusion-based pipelines show slow generation speed due to dozens of inference steps. To address these two challenges, we propose GestureLSM, a flow-matching-based approach for Co-Speech Gesture Generation with spatial-temporal modeling. Our method i) explicitly "},"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":"2501.18898","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T05:34:59Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"1dd041c894d61938716fa4e9572b9b7db9201aa0d29d5a22e5dcc7cd679239c4","abstract_canon_sha256":"665ff2ece66f06b6237fc112afc89a099bc1df46bc44aed3429e059060d23ee6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:18.536744Z","signature_b64":"x3N7dzDaOpXuSck0zMRXhoukTXTgofOOINm0q1HBkyZeexDhLX2LhaKPf0irysPbGRoBRhGeCEtxpXUbCkbEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4328c624a56379dbbcf4213ecde797c89a10808db6051997839627c3b5ba1daf","last_reissued_at":"2026-07-05T11:47:18.536238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:18.536238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Haiyang Liu, Junhua Huang, Luchuan Song, Pinxin Liu","submitted_at":"2025-01-31T05:34:59Z","abstract_excerpt":"Generating full-body human gestures based on speech signals remains challenges on quality and speed. Existing approaches model different body regions such as body, legs and hands separately, which fail to capture the spatial interactions between them and result in unnatural and disjointed movements. Additionally, their autoregressive/diffusion-based pipelines show slow generation speed due to dozens of inference steps. To address these two challenges, we propose GestureLSM, a flow-matching-based approach for Co-Speech Gesture Generation with spatial-temporal modeling. Our method i) explicitly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18898","kind":"arxiv","version":3},"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/2501.18898/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":"2501.18898","created_at":"2026-07-05T11:47:18.536301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18898v3","created_at":"2026-07-05T11:47:18.536301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18898","created_at":"2026-07-05T11:47:18.536301+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMUMMJFFMN45","created_at":"2026-07-05T11:47:18.536301+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMUMMJFFMN45XPHU","created_at":"2026-07-05T11:47:18.536301+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMUMMJFF","created_at":"2026-07-05T11:47:18.536301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03874","citing_title":"DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06063","citing_title":"Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06063","citing_title":"Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC","json":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC.json","graph_json":"https://pith.science/api/pith-number/IMUMMJFFMN45XPHUEE7M3Z4XZC/graph.json","events_json":"https://pith.science/api/pith-number/IMUMMJFFMN45XPHUEE7M3Z4XZC/events.json","paper":"https://pith.science/paper/IMUMMJFF"},"agent_actions":{"view_html":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC","download_json":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC.json","view_paper":"https://pith.science/paper/IMUMMJFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18898&json=true","fetch_graph":"https://pith.science/api/pith-number/IMUMMJFFMN45XPHUEE7M3Z4XZC/graph.json","fetch_events":"https://pith.science/api/pith-number/IMUMMJFFMN45XPHUEE7M3Z4XZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC/action/storage_attestation","attest_author":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC/action/author_attestation","sign_citation":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC/action/citation_signature","submit_replication":"https://pith.science/pith/IMUMMJFFMN45XPHUEE7M3Z4XZC/action/replication_record"}},"created_at":"2026-07-05T11:47:18.536301+00:00","updated_at":"2026-07-05T11:47:18.536301+00:00"}