{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XPVQRA5GJLIHOMIHKRFVPPRDRD","short_pith_number":"pith:XPVQRA5G","schema_version":"1.0","canonical_sha256":"bbeb0883a64ad0773107544b57be2388e0285343bc2c86b2228b2673a0396ee6","source":{"kind":"arxiv","id":"2506.01077","version":1},"attestation_state":"computed","paper":{"title":"TRiMM: Transformer-Based Rich Motion Matching for Real-Time multi-modal Interaction in Digital Humans","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.GR","authors_text":"Fan Zhang, Helin Li, Jiehaolin Chen, Sirui Xiao, Tianzhao Li, Xin Lyu, Yezi He, Yueqian Guo, Yurun Chen, Zhaohan Wang","submitted_at":"2025-06-01T16:27:24Z","abstract_excerpt":"Large Language Model (LLM)-driven digital humans have sparked a series of recent studies on co-speech gesture generation systems. However, existing approaches struggle with real-time synthesis and long-text comprehension. This paper introduces Transformer-Based Rich Motion Matching (TRiMM), a novel multi-modal framework for real-time 3D gesture generation. Our method incorporates three modules: 1) a cross-modal attention mechanism to achieve precise temporal alignment between speech and gestures; 2) a long-context autoregressive model with a sliding window mechanism for effective sequence mode"},"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":"2506.01077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.GR","submitted_at":"2025-06-01T16:27:24Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"d0fc1c5f509a18c31ff8c48a21cb4e56525c0e2d8960dc601870a38275a56f45","abstract_canon_sha256":"5b2e66c4273398167f181a0af63ae4fe39f3f3a89f575cdeb2414bc02dda4f52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:45.793196Z","signature_b64":"Ba8pFUFuG+TTkVmYJ/iBJJt1r/D5vs8Lr5VNprL6YVQHN2UBwK6jhpJtaahSgTwpRrLNjQvPfflPF0ThZqpmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbeb0883a64ad0773107544b57be2388e0285343bc2c86b2228b2673a0396ee6","last_reissued_at":"2026-07-05T11:13:45.792504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:45.792504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRiMM: Transformer-Based Rich Motion Matching for Real-Time multi-modal Interaction in Digital Humans","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.GR","authors_text":"Fan Zhang, Helin Li, Jiehaolin Chen, Sirui Xiao, Tianzhao Li, Xin Lyu, Yezi He, Yueqian Guo, Yurun Chen, Zhaohan Wang","submitted_at":"2025-06-01T16:27:24Z","abstract_excerpt":"Large Language Model (LLM)-driven digital humans have sparked a series of recent studies on co-speech gesture generation systems. However, existing approaches struggle with real-time synthesis and long-text comprehension. This paper introduces Transformer-Based Rich Motion Matching (TRiMM), a novel multi-modal framework for real-time 3D gesture generation. Our method incorporates three modules: 1) a cross-modal attention mechanism to achieve precise temporal alignment between speech and gestures; 2) a long-context autoregressive model with a sliding window mechanism for effective sequence mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01077","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/2506.01077/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":"2506.01077","created_at":"2026-07-05T11:13:45.792584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01077v1","created_at":"2026-07-05T11:13:45.792584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01077","created_at":"2026-07-05T11:13:45.792584+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPVQRA5GJLIH","created_at":"2026-07-05T11:13:45.792584+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPVQRA5GJLIHOMIH","created_at":"2026-07-05T11:13:45.792584+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPVQRA5G","created_at":"2026-07-05T11:13:45.792584+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/XPVQRA5GJLIHOMIHKRFVPPRDRD","json":"https://pith.science/pith/XPVQRA5GJLIHOMIHKRFVPPRDRD.json","graph_json":"https://pith.science/api/pith-number/XPVQRA5GJLIHOMIHKRFVPPRDRD/graph.json","events_json":"https://pith.science/api/pith-number/XPVQRA5GJLIHOMIHKRFVPPRDRD/events.json","paper":"https://pith.science/paper/XPVQRA5G"},"agent_actions":{"view_html":"https://pith.science/pith/XPVQRA5GJLIHOMIHKRFVPPRDRD","download_json":"https://pith.science/pith/XPVQRA5GJLIHOMIHKRFVPPRDRD.json","view_paper":"https://pith.science/paper/XPVQRA5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01077&json=true","fetch_graph":"https://pith.science/api/pith-number/XPVQRA5GJLIHOMIHKRFVPPRDRD/graph.json","fetch_events":"https://pith.science/api/pith-number/XPVQRA5GJLIHOMIHKRFVPPRDRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPVQRA5GJLIHOMIHKRFVPPRDRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPVQRA5GJLIHOMIHKRFVPPRDRD/action/storage_attestation","attest_author":"https://pith.science/pith/XPVQRA5GJLIHOMIHKRFVPPRDRD/action/author_attestation","sign_citation":"https://pith.science/pith/XPVQRA5GJLIHOMIHKRFVPPRDRD/action/citation_signature","submit_replication":"https://pith.science/pith/XPVQRA5GJLIHOMIHKRFVPPRDRD/action/replication_record"}},"created_at":"2026-07-05T11:13:45.792584+00:00","updated_at":"2026-07-05T11:13:45.792584+00:00"}