{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X6PJYWIAU3RLQZTN26VSKQ7M5P","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":"ebbc8fed680b873cfab82d11862a14991bb5325c5ab89426ac110b5616dcdc33","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-07T13:24:54Z","title_canon_sha256":"333e03d427a3a0857edaa59032419ed887cbc1e7977bc6ee1cfdb239d08a043f"},"schema_version":"1.0","source":{"id":"2407.05361","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05361","created_at":"2026-07-05T09:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05361v3","created_at":"2026-07-05T09:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05361","created_at":"2026-07-05T09:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"X6PJYWIAU3RL","created_at":"2026-07-05T09:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"X6PJYWIAU3RLQZTN","created_at":"2026-07-05T09:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"X6PJYWIA","created_at":"2026-07-05T09:04:11Z"}],"graph_snapshots":[{"event_id":"sha256:c4c542e446e42d69ae40ae43cb319378808ca9d574d0b80bc00d0a3a79ff4a3b","target":"graph","created_at":"2026-07-05T09:04:11Z","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/2407.05361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in speech generation models have been significantly driven by the use of large-scale training data. However, producing highly spontaneous, human-like speech remains a challenge due to the scarcity of large, diverse, and spontaneous speech datasets. In response, we introduce Emilia, the first large-scale, multilingual, and diverse speech generation dataset. Emilia starts with over 101k hours of speech across six languages, covering a wide range of speaking styles to enable more natural and spontaneous speech generation. To facilitate the scale-up of Emilia, we also present E","authors_text":"Chaoren Wang, Chen Yang, Haorui He, Hua Hua, Jiaqi Li, Kai Chen, Liwei Liu, Peiyang Shi, Pengyuan Zhang, Xuyuan Li, Yicheng Gu, Yuancheng Wang, Zengqiang Shang, Zhizheng Wu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-07T13:24:54Z","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05361","kind":"arxiv","version":3},"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":"sha256:6844c991390d0e69ddfb221e2a925495aff180da18ee1b2781eb24ae4d211657","target":"record","created_at":"2026-07-05T09:04:11Z","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":"ebbc8fed680b873cfab82d11862a14991bb5325c5ab89426ac110b5616dcdc33","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-07T13:24:54Z","title_canon_sha256":"333e03d427a3a0857edaa59032419ed887cbc1e7977bc6ee1cfdb239d08a043f"},"schema_version":"1.0","source":{"id":"2407.05361","kind":"arxiv","version":3}},"canonical_sha256":"bf9e9c5900a6e2b8666dd7ab2543ecebde0c333a6fd8eddcfe16708666db9e9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf9e9c5900a6e2b8666dd7ab2543ecebde0c333a6fd8eddcfe16708666db9e9d","first_computed_at":"2026-07-05T09:04:11.096098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:11.096098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a1qWIDHHLCOwOnBV3EQBrU5vNsyf41wcedYpFshGpBNq8uPioWZaBP8DWqP/EgsAIJlU8EnrlKXEGrZvKcu4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:11.096592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05361","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6844c991390d0e69ddfb221e2a925495aff180da18ee1b2781eb24ae4d211657","sha256:c4c542e446e42d69ae40ae43cb319378808ca9d574d0b80bc00d0a3a79ff4a3b"],"state_sha256":"5ca89081244bc4c975d6ba6d3a46321048dffdccf9f4ea7ed9b217c29cc617c8"}