{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3SY7DGRF3532WH6FXK7XDO4ANS","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":"941fc5b3cd4c15fa9319e21afb707c6192ccbebbd04842b14f6f6eaa1e61b06f","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-23T08:45:57Z","title_canon_sha256":"1256413aa54dce782fce048e973115172ce04b274babd8686b1ab23f6a3570cf"},"schema_version":"1.0","source":{"id":"2312.15197","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15197","created_at":"2026-07-05T07:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15197v1","created_at":"2026-07-05T07:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15197","created_at":"2026-07-05T07:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"3SY7DGRF3532","created_at":"2026-07-05T07:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"3SY7DGRF3532WH6F","created_at":"2026-07-05T07:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"3SY7DGRF","created_at":"2026-07-05T07:27:32Z"}],"graph_snapshots":[{"event_id":"sha256:c892fa44f57367bc9837192c3875bea875ee9c88d27a4114895cec323f0f2541","target":"graph","created_at":"2026-07-05T07:27:32Z","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/2312.15197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct speech-to-speech translation achieves high-quality results through the introduction of discrete units obtained from self-supervised learning. This approach circumvents delays and cascading errors associated with model cascading. However, talking head translation, converting audio-visual speech (i.e., talking head video) from one language into another, still confronts several challenges compared to audio speech: (1) Existing methods invariably rely on cascading, synthesizing via both audio and text, resulting in delays and cascading errors. (2) Talking head translation has a limited set ","authors_text":"Aoxiong Yin, Changpeng Yang, Linjun Li, Minglei Li, Rongjie Huang, Tao Jin, Xinyu Duan, Xize Cheng, Zehan Wang, Zhou Zhao","cross_cats":["cs.CL","cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-23T08:45:57Z","title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15197","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:bc1b26c675ce72514c2910b7bcff99d6258cb3cff83646dcd846bfe585ee25f3","target":"record","created_at":"2026-07-05T07:27:32Z","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":"941fc5b3cd4c15fa9319e21afb707c6192ccbebbd04842b14f6f6eaa1e61b06f","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-23T08:45:57Z","title_canon_sha256":"1256413aa54dce782fce048e973115172ce04b274babd8686b1ab23f6a3570cf"},"schema_version":"1.0","source":{"id":"2312.15197","kind":"arxiv","version":1}},"canonical_sha256":"dcb1f19a25df77ab1fc5babf71bb806c8020c27b0e9749f0ef4d313a4724f4ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcb1f19a25df77ab1fc5babf71bb806c8020c27b0e9749f0ef4d313a4724f4ed","first_computed_at":"2026-07-05T07:27:32.176034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:32.176034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gHEjoGUd5m7sl1jYo0ISCbCs2Z1zoNKpkKt6xH3sfBYiBM2OHx6oLqvlCmaDUu0tb4hUpJKLqdC0Ob1RNPTNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:32.176520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15197","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc1b26c675ce72514c2910b7bcff99d6258cb3cff83646dcd846bfe585ee25f3","sha256:c892fa44f57367bc9837192c3875bea875ee9c88d27a4114895cec323f0f2541"],"state_sha256":"8fae2ec22eab72ea6f98b0fda4e542ad9644f77799df45dfde3a1a5d2e089ed1"}