{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6ERWEOVFOZDTBY3OZPTNLBCRVC","short_pith_number":"pith:6ERWEOVF","canonical_record":{"source":{"id":"2605.14731","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-14T11:56:03Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"d584906bda4e0230135b4e0174403a0d28358cf4c19214f7224f809c82207fef","abstract_canon_sha256":"6974c45483e65b7fb45b827ead0efc95b2a5edd8d955e993504cac79cc0e3355"},"schema_version":"1.0"},"canonical_sha256":"f123623aa5764730e36ecbe6d58451a880fe60169309e60ab9846270057f316a","source":{"kind":"arxiv","id":"2605.14731","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14731","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14731v1","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14731","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"6ERWEOVFOZDT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6ERWEOVFOZDTBY3O","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6ERWEOVF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6ERWEOVFOZDTBY3OZPTNLBCRVC","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14731","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-14T11:56:03Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"d584906bda4e0230135b4e0174403a0d28358cf4c19214f7224f809c82207fef","abstract_canon_sha256":"6974c45483e65b7fb45b827ead0efc95b2a5edd8d955e993504cac79cc0e3355"},"schema_version":"1.0"},"canonical_sha256":"f123623aa5764730e36ecbe6d58451a880fe60169309e60ab9846270057f316a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:59.023424Z","signature_b64":"nQeWYZWt8tTTqqdh49uVVlVkDXPZTBrUU9gkSIDl+H32H0JXt761ZZ+F8FFAYPg7L6tYuSQ0qSIYuq8XMGiNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f123623aa5764730e36ecbe6d58451a880fe60169309e60ab9846270057f316a","last_reissued_at":"2026-05-17T23:38:59.022837Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:59.022837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14731","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":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yZAJZYCFqGInzcS/qAcLLR36S6G5AffMEfKu/jj69TwGxGOQpC4DXCbqZfM/UPxnPBB6b3+9PHy/66oA5Oq/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:24:01.053490Z"},"content_sha256":"42cdfa9f4681125874e1ebcd2b521e043a54017a5de9aeb679cb70662c8d2087","schema_version":"1.0","event_id":"sha256:42cdfa9f4681125874e1ebcd2b521e043a54017a5de9aeb679cb70662c8d2087"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6ERWEOVFOZDTBY3OZPTNLBCRVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"cs.GR","authors_text":"Chenghao Yang, Dongjie Fu, Hansung Kim, Jie Guo, Pengcheng Fang, Tengjiao Sun, Xiaohao Cai, Xiaohong Zhang, Xiaoyu Zhan, Xinyu Fu, Yanwen Guo, Yuanqi Li","submitted_at":"2026-05-14T11:56:03Z","abstract_excerpt":"Speech-driven gestures and facial animations are fundamental to expressive digital avatars in games, virtual production, and interactive media. However, existing methods are either limited to a single modality for audio motion alignment, failing to fully utilize the potential of massive human motion data, or are constrained by the representation ability and throughput of multimodal models, which makes it difficult to achieve high-quality motion generation or real-time performance. We present UMo, a unified sparse motion modeling architecture for real-time co-speech avatars, which processes tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14731","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":""},"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":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mLJS2qBzsX+IvgZanUWaA8X6N4/uk1QJl/oOE/8uCoQWhbXioS5mbgCYmjZMkSmmN1ZEow/AWSepInnOsaOyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T10:24:01.053843Z"},"content_sha256":"bb641735557efe3f9c90658e8768fbf404614abcf1d885b1be8b0a1774c6201c","schema_version":"1.0","event_id":"sha256:bb641735557efe3f9c90658e8768fbf404614abcf1d885b1be8b0a1774c6201c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ERWEOVFOZDTBY3OZPTNLBCRVC/bundle.json","state_url":"https://pith.science/pith/6ERWEOVFOZDTBY3OZPTNLBCRVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ERWEOVFOZDTBY3OZPTNLBCRVC/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":"2026-06-11T10:24:01Z","links":{"resolver":"https://pith.science/pith/6ERWEOVFOZDTBY3OZPTNLBCRVC","bundle":"https://pith.science/pith/6ERWEOVFOZDTBY3OZPTNLBCRVC/bundle.json","state":"https://pith.science/pith/6ERWEOVFOZDTBY3OZPTNLBCRVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ERWEOVFOZDTBY3OZPTNLBCRVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6ERWEOVFOZDTBY3OZPTNLBCRVC","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":"6974c45483e65b7fb45b827ead0efc95b2a5edd8d955e993504cac79cc0e3355","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-14T11:56:03Z","title_canon_sha256":"d584906bda4e0230135b4e0174403a0d28358cf4c19214f7224f809c82207fef"},"schema_version":"1.0","source":{"id":"2605.14731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14731","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14731v1","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14731","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"6ERWEOVFOZDT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6ERWEOVFOZDTBY3O","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6ERWEOVF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:bb641735557efe3f9c90658e8768fbf404614abcf1d885b1be8b0a1774c6201c","target":"graph","created_at":"2026-05-17T23:38:59Z","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"},"paper":{"abstract_excerpt":"Speech-driven gestures and facial animations are fundamental to expressive digital avatars in games, virtual production, and interactive media. However, existing methods are either limited to a single modality for audio motion alignment, failing to fully utilize the potential of massive human motion data, or are constrained by the representation ability and throughput of multimodal models, which makes it difficult to achieve high-quality motion generation or real-time performance. We present UMo, a unified sparse motion modeling architecture for real-time co-speech avatars, which processes tex","authors_text":"Chenghao Yang, Dongjie Fu, Hansung Kim, Jie Guo, Pengcheng Fang, Tengjiao Sun, Xiaohao Cai, Xiaohong Zhang, Xiaoyu Zhan, Xinyu Fu, Yanwen Guo, Yuanqi Li","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-14T11:56:03Z","title":"UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14731","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":"sha256:42cdfa9f4681125874e1ebcd2b521e043a54017a5de9aeb679cb70662c8d2087","target":"record","created_at":"2026-05-17T23:38:59Z","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":"6974c45483e65b7fb45b827ead0efc95b2a5edd8d955e993504cac79cc0e3355","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-14T11:56:03Z","title_canon_sha256":"d584906bda4e0230135b4e0174403a0d28358cf4c19214f7224f809c82207fef"},"schema_version":"1.0","source":{"id":"2605.14731","kind":"arxiv","version":1}},"canonical_sha256":"f123623aa5764730e36ecbe6d58451a880fe60169309e60ab9846270057f316a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f123623aa5764730e36ecbe6d58451a880fe60169309e60ab9846270057f316a","first_computed_at":"2026-05-17T23:38:59.022837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:59.022837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nQeWYZWt8tTTqqdh49uVVlVkDXPZTBrUU9gkSIDl+H32H0JXt761ZZ+F8FFAYPg7L6tYuSQ0qSIYuq8XMGiNDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:59.023424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14731","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42cdfa9f4681125874e1ebcd2b521e043a54017a5de9aeb679cb70662c8d2087","sha256:bb641735557efe3f9c90658e8768fbf404614abcf1d885b1be8b0a1774c6201c"],"state_sha256":"240d6e1bdacaf7bbfb495c28b93e557c0974cbd26706ea8bffd4478e3317dae5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6gDeraAvcwP8evkzoIk64NaB3TOdo77XABrnTra5+SzjtHIEooYEAZC0ghp8cFZYupgcsExXPJztD9FUqU/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T10:24:01.055838Z","bundle_sha256":"d0f806b61a558e5a606f5acbe1f29959aa536057c61389f6189caf93934003bf"}}