{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A6NMDBPZHD5HQLKCVINEM7K2GG","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":"a6ed188262192e84831b4730a9011b53736f8a97bf6042961fae6acd6bb0b825","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T14:39:16Z","title_canon_sha256":"fc6dfc7ec188319b0b127245952edd10de57a8ffaa4a99b83103f74c7076a4ae"},"schema_version":"1.0","source":{"id":"2402.05712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05712","created_at":"2026-07-05T07:43:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05712v1","created_at":"2026-07-05T07:43:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05712","created_at":"2026-07-05T07:43:02Z"},{"alias_kind":"pith_short_12","alias_value":"A6NMDBPZHD5H","created_at":"2026-07-05T07:43:02Z"},{"alias_kind":"pith_short_16","alias_value":"A6NMDBPZHD5HQLKC","created_at":"2026-07-05T07:43:02Z"},{"alias_kind":"pith_short_8","alias_value":"A6NMDBPZ","created_at":"2026-07-05T07:43:02Z"}],"graph_snapshots":[{"event_id":"sha256:a548d6c64de3080043171719b84d2a8bc30788c954eecf36c2d8bb707dd465f2","target":"graph","created_at":"2026-07-05T07:43:02Z","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/2402.05712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for this task. However, their mere aggregation does not lead to improved performance. We suspect this is due to a shortage of paired audio-4D data, which is crucial for the Transformer to effectively perform as a denoiser within the Diffusion framework. To tackle this issue, we present DiffSpeaker, a Transformer-based network equipped with novel biased conditional attention modules. These modules serve as substitutes for th","authors_text":"Chen Qian, Guojun Qi, Xiangyu Zhu, Zhaoxiang Zhang, Zhen Lei, Zhiyuan Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T14:39:16Z","title":"DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05712","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":"sha256:86744687c86a423d88fc8d112a76892ac90652b2210463df97f4f0305fefa142","target":"record","created_at":"2026-07-05T07:43:02Z","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":"a6ed188262192e84831b4730a9011b53736f8a97bf6042961fae6acd6bb0b825","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T14:39:16Z","title_canon_sha256":"fc6dfc7ec188319b0b127245952edd10de57a8ffaa4a99b83103f74c7076a4ae"},"schema_version":"1.0","source":{"id":"2402.05712","kind":"arxiv","version":1}},"canonical_sha256":"079ac185f938fa782d42aa1a467d5a31b4874ae12889fe380191693130af9d0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"079ac185f938fa782d42aa1a467d5a31b4874ae12889fe380191693130af9d0a","first_computed_at":"2026-07-05T07:43:02.376487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:02.376487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GkyFjjPg6iFzBKQmazuvTvYZKN0+WANQ+xvNpH2EDivQnrhqRNil50O88Mtbf7kz12bvS1jqUZWcHI8ChuiEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:02.376901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86744687c86a423d88fc8d112a76892ac90652b2210463df97f4f0305fefa142","sha256:a548d6c64de3080043171719b84d2a8bc30788c954eecf36c2d8bb707dd465f2"],"state_sha256":"74362b205d6cf43cc3d9cda141cb874409f14763f241a3dd5a74784620eb67cc"}