{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YTAC3FXOUBNT4FHXVT6MSJEDAT","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":"daf21fe38a8095f07e52349a061950dd19709912a819818cba61371388593a6b","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-08T10:23:20Z","title_canon_sha256":"f7d1d289bfffe9d81627d706c8306d85742d75f6000258e8ee4929edd69e4b26"},"schema_version":"1.0","source":{"id":"2502.05512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05512","created_at":"2026-07-05T10:11:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05512v1","created_at":"2026-07-05T10:11:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05512","created_at":"2026-07-05T10:11:39Z"},{"alias_kind":"pith_short_12","alias_value":"YTAC3FXOUBNT","created_at":"2026-07-05T10:11:39Z"},{"alias_kind":"pith_short_16","alias_value":"YTAC3FXOUBNT4FHX","created_at":"2026-07-05T10:11:39Z"},{"alias_kind":"pith_short_8","alias_value":"YTAC3FXO","created_at":"2026-07-05T10:11:39Z"}],"graph_snapshots":[{"event_id":"sha256:542a1d7ea89f40daa3005e93a2ee381d56181226dabec6ed3d475066ddf0d2a6","target":"graph","created_at":"2026-07-05T10:11:39Z","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/2502.05512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, large language model (LLM) based text-to-speech (TTS) systems have gradually become the mainstream in the industry due to their high naturalness and powerful zero-shot voice cloning capabilities.Here, we introduce the IndexTTS system, which is mainly based on the XTTS and Tortoise model. We add some novel improvements. Specifically, in Chinese scenarios, we adopt a hybrid modeling method that combines characters and pinyin, making the pronunciations of polyphonic characters and long-tail characters controllable. We also performed a comparative analysis of the Vector Quantization (VQ)","authors_text":"Jinchao Wang, Jingchen Shu, Lu Wang, Siyi Zhou, Wei Deng","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-08T10:23:20Z","title":"IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05512","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:edaf82931d8c066391f88852712629fc39af0a8db6a1f3926ec452fe49e64207","target":"record","created_at":"2026-07-05T10:11:39Z","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":"daf21fe38a8095f07e52349a061950dd19709912a819818cba61371388593a6b","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-08T10:23:20Z","title_canon_sha256":"f7d1d289bfffe9d81627d706c8306d85742d75f6000258e8ee4929edd69e4b26"},"schema_version":"1.0","source":{"id":"2502.05512","kind":"arxiv","version":1}},"canonical_sha256":"c4c02d96eea05b3e14f7acfcc9248304f984c8b87af89563cc89d2fa4cda3271","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4c02d96eea05b3e14f7acfcc9248304f984c8b87af89563cc89d2fa4cda3271","first_computed_at":"2026-07-05T10:11:39.240697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:39.240697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u+r/m6qRhoeOroubpi0fz8uKcWBIJebYnhL0ZmuqWftWILfia8FB9tboXWD7YnyFhdK4nSLvEKHmV7DwgZEFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:39.241147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edaf82931d8c066391f88852712629fc39af0a8db6a1f3926ec452fe49e64207","sha256:542a1d7ea89f40daa3005e93a2ee381d56181226dabec6ed3d475066ddf0d2a6"],"state_sha256":"67d01680edbd4addcadff1b7d7f6ec1934721fc5ce37962879e6baa522d183ef"}