{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPVQRA5GJLIHOMIHKRFVPPRDRD","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":"5b2e66c4273398167f181a0af63ae4fe39f3f3a89f575cdeb2414bc02dda4f52","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.GR","submitted_at":"2025-06-01T16:27:24Z","title_canon_sha256":"d0fc1c5f509a18c31ff8c48a21cb4e56525c0e2d8960dc601870a38275a56f45"},"schema_version":"1.0","source":{"id":"2506.01077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01077","created_at":"2026-07-05T11:13:45Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01077v1","created_at":"2026-07-05T11:13:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01077","created_at":"2026-07-05T11:13:45Z"},{"alias_kind":"pith_short_12","alias_value":"XPVQRA5GJLIH","created_at":"2026-07-05T11:13:45Z"},{"alias_kind":"pith_short_16","alias_value":"XPVQRA5GJLIHOMIH","created_at":"2026-07-05T11:13:45Z"},{"alias_kind":"pith_short_8","alias_value":"XPVQRA5G","created_at":"2026-07-05T11:13:45Z"}],"graph_snapshots":[{"event_id":"sha256:80d14307c70f7a7e4f450693157cd1048fabf6d1987ba929915956def4ea72b9","target":"graph","created_at":"2026-07-05T11:13:45Z","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/2506.01077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fan Zhang, Helin Li, Jiehaolin Chen, Sirui Xiao, Tianzhao Li, Xin Lyu, Yezi He, Yueqian Guo, Yurun Chen, Zhaohan Wang","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.GR","submitted_at":"2025-06-01T16:27:24Z","title":"TRiMM: Transformer-Based Rich Motion Matching for Real-Time multi-modal Interaction in Digital Humans"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01077","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":"sha256:979856ebe9f119ba9bdc390ffa76ef7c0986d4979af6afc791bfe6761c19921d","target":"record","created_at":"2026-07-05T11:13:45Z","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":"5b2e66c4273398167f181a0af63ae4fe39f3f3a89f575cdeb2414bc02dda4f52","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.GR","submitted_at":"2025-06-01T16:27:24Z","title_canon_sha256":"d0fc1c5f509a18c31ff8c48a21cb4e56525c0e2d8960dc601870a38275a56f45"},"schema_version":"1.0","source":{"id":"2506.01077","kind":"arxiv","version":1}},"canonical_sha256":"bbeb0883a64ad0773107544b57be2388e0285343bc2c86b2228b2673a0396ee6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbeb0883a64ad0773107544b57be2388e0285343bc2c86b2228b2673a0396ee6","first_computed_at":"2026-07-05T11:13:45.792504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:45.792504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ba8pFUFuG+TTkVmYJ/iBJJt1r/D5vs8Lr5VNprL6YVQHN2UBwK6jhpJtaahSgTwpRrLNjQvPfflPF0ThZqpmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:45.793196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:979856ebe9f119ba9bdc390ffa76ef7c0986d4979af6afc791bfe6761c19921d","sha256:80d14307c70f7a7e4f450693157cd1048fabf6d1987ba929915956def4ea72b9"],"state_sha256":"1500b48c44318858c1a352554b23347e891c2b4da8b9bb13ba1162d09340c8d4"}