{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6IQJSMT7NXRJEOH644XYWNJF25","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":"356b537e2299105ff2da0cfb3bd91e3c85cfe5d1645fc6a8ce01423d10e14469","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T08:31:15Z","title_canon_sha256":"a696c5d48e1d620372d3480f1cb7bd6aa52f1bfb6318632c2c8f1fe9fbbaac44"},"schema_version":"1.0","source":{"id":"2508.13618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13618","created_at":"2026-07-05T11:55:51Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13618v1","created_at":"2026-07-05T11:55:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13618","created_at":"2026-07-05T11:55:51Z"},{"alias_kind":"pith_short_12","alias_value":"6IQJSMT7NXRJ","created_at":"2026-07-05T11:55:51Z"},{"alias_kind":"pith_short_16","alias_value":"6IQJSMT7NXRJEOH6","created_at":"2026-07-05T11:55:51Z"},{"alias_kind":"pith_short_8","alias_value":"6IQJSMT7","created_at":"2026-07-05T11:55:51Z"}],"graph_snapshots":[{"event_id":"sha256:7b96a2183760d1bc5613c64b94183370b84912ed9da8694f5f607367bb85b5f4","target":"graph","created_at":"2026-07-05T11:55:51Z","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/2508.13618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-driven talking head synthesis has achieved remarkable photorealism, yet state-of-the-art (SOTA) models exhibit a critical failure: they lack generalization to the full spectrum of human diversity in ethnicity, language, and age groups. We argue that this generalization gap is a direct symptom of limitations in existing training data, which lack the necessary scale, quality, and diversity. To address this challenge, we introduce TalkVid, a new large-scale, high-quality, and diverse dataset containing 1244 hours of video from 7729 unique speakers. TalkVid is curated through a principled, m","authors_text":"Benyou Wang, Chenghao Zhu, Guanbin Li, Harry Yang, Hejin Huang, Junying Chen, Michael Guan, Pengcheng Chen, Rongsheng Wang, Ser-Nam Lim, Shunian Chen, Yexin Liu, Zihan Ye","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T08:31:15Z","title":"TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13618","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":"sha256:821abf0ccfa183d60691348026085b75509b145658787c75878149b466ec4ba7","target":"record","created_at":"2026-07-05T11:55:51Z","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":"356b537e2299105ff2da0cfb3bd91e3c85cfe5d1645fc6a8ce01423d10e14469","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T08:31:15Z","title_canon_sha256":"a696c5d48e1d620372d3480f1cb7bd6aa52f1bfb6318632c2c8f1fe9fbbaac44"},"schema_version":"1.0","source":{"id":"2508.13618","kind":"arxiv","version":1}},"canonical_sha256":"f22099327f6de29238fee72f8b3525d74335dbde77580d82efc4c3edb0a003a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f22099327f6de29238fee72f8b3525d74335dbde77580d82efc4c3edb0a003a6","first_computed_at":"2026-07-05T11:55:51.265932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:51.265932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xOpBVQwH0mB1+9J9Vgu/Rt7+yPSYQgQ6rUMicAzsVFL7yyf9K8UcAS770s1IxKUet3jetTsCdd1FDrjQh6/6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:51.266481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.13618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:821abf0ccfa183d60691348026085b75509b145658787c75878149b466ec4ba7","sha256:7b96a2183760d1bc5613c64b94183370b84912ed9da8694f5f607367bb85b5f4"],"state_sha256":"2a6077b39739275d8463b902506058d6a73ecf4ada8b0704a8c47dc05d9b6a24"}