{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3DDX5YK2MZQC6EI4CLT7PMLKTK","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":"d949c03e7ba93ae178a50e5ccc8be5300ca7d9062cbee6970ef97773eb808a9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-06T17:29:01Z","title_canon_sha256":"9433da1536fa5139f62595593425bd7879f36b9acdfa1a8e290c0e91e020d42e"},"schema_version":"1.0","source":{"id":"2408.03312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03312","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03312v1","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03312","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_12","alias_value":"3DDX5YK2MZQC","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_16","alias_value":"3DDX5YK2MZQC6EI4","created_at":"2026-07-05T08:52:48Z"},{"alias_kind":"pith_short_8","alias_value":"3DDX5YK2","created_at":"2026-07-05T08:52:48Z"}],"graph_snapshots":[{"event_id":"sha256:a51bd6583e14c59fb7487a365dcbde73cca3bcc792cfacdf3a254df2285e5c13","target":"graph","created_at":"2026-07-05T08:52:48Z","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/2408.03312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in the field of Diffusion Transformers have substantially improved the generation of high-quality 2D images, 3D videos, and 3D shapes. However, the effectiveness of the Transformer architecture in the domain of co-speech gesture generation remains relatively unexplored, as prior methodologies have predominantly employed the Convolutional Neural Network (CNNs) or simple a few transformer layers. In an attempt to bridge this research gap, we introduce a novel Masked Diffusion Transformer for co-speech gesture generation, referred to as MDT-A2G, which directly implements the d","authors_text":"Chencan Fu, Chengjie Wang, Jiafu Wu, Jiangning Zhang, Mingmin Chi, Qilin Wang, Wei Li, Xiaofeng Mao, Yabiao Wang, Zhengkai Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-06T17:29:01Z","title":"MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03312","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":"sha256:794e2ce58c67d5e7f11cf63f7059fed4ac5206f77f532e98aaed6bdb9274c2f1","target":"record","created_at":"2026-07-05T08:52:48Z","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":"d949c03e7ba93ae178a50e5ccc8be5300ca7d9062cbee6970ef97773eb808a9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-06T17:29:01Z","title_canon_sha256":"9433da1536fa5139f62595593425bd7879f36b9acdfa1a8e290c0e91e020d42e"},"schema_version":"1.0","source":{"id":"2408.03312","kind":"arxiv","version":1}},"canonical_sha256":"d8c77ee15a66602f111c12e7f7b16a9ab12774cc9b222c1079ccb8808f2f2b65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8c77ee15a66602f111c12e7f7b16a9ab12774cc9b222c1079ccb8808f2f2b65","first_computed_at":"2026-07-05T08:52:48.812991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:48.812991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jENtit/8R+wSdDe92f8/axj3J0F4SNYR4V45NREqINoJ65TG+QGhrJOvCG0eaXnJY3PfIbWEknb0eIuasJI/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:48.813436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:794e2ce58c67d5e7f11cf63f7059fed4ac5206f77f532e98aaed6bdb9274c2f1","sha256:a51bd6583e14c59fb7487a365dcbde73cca3bcc792cfacdf3a254df2285e5c13"],"state_sha256":"59602fda7f2a6128475620e004f840b0b9e2f82c011f5390f28be474746f0171"}