{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JVYG2IAEO4G6DMA2BTTMECR6CF","short_pith_number":"pith:JVYG2IAE","schema_version":"1.0","canonical_sha256":"4d706d2004770de1b01a0ce6c20a3e11541a1db0f48e3556b7c108ebb85f155f","source":{"kind":"arxiv","id":"2605.27258","version":1},"attestation_state":"computed","paper":{"title":"PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Bowen Li, Dongrui Li, Jiahui Zhao, Keming Chen, Mingli Jin, Shaotong Guo, Weibo Xiong, Yang Xiang, Yihang Lin, Yue Liu, Yunze Gao, Yuze Zhou, Zeyang Lin, Zhen Wang","submitted_at":"2026-05-26T16:36:56Z","abstract_excerpt":"Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers for resource-constrained research teams. In this report, we present PilotTTS, a lightweight autoregressive TTS system that achieves competitive performance through minimalist architecture and rigorous data engineering. PilotTTS is trained on only 200K hours of data processed entirely with open-source tools. Specifically, our contributions are: (1) a reproducible multi-stage data processing pipeline covering quality a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.27258","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-26T16:36:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3223e1fc1047b45657f1ff2f9a272a4a7661e374f859751850adca19a2b75fdf","abstract_canon_sha256":"f1bd9ae14b3c848583bc36eb99e11a4a7799f7e20ac2c399aaf8ec4549b8b044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:08.763663Z","signature_b64":"87C4+swZ58srruV/igp2DR4SOYCyJ4j7hRV5Z3+7X/+45obFs9wxtmco22hPgIewWjWDiqmuIKxI22auDKEuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d706d2004770de1b01a0ce6c20a3e11541a1db0f48e3556b7c108ebb85f155f","last_reissued_at":"2026-05-27T02:06:08.763188Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:08.763188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Bowen Li, Dongrui Li, Jiahui Zhao, Keming Chen, Mingli Jin, Shaotong Guo, Weibo Xiong, Yang Xiang, Yihang Lin, Yue Liu, Yunze Gao, Yuze Zhou, Zeyang Lin, Zhen Wang","submitted_at":"2026-05-26T16:36:56Z","abstract_excerpt":"Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers for resource-constrained research teams. In this report, we present PilotTTS, a lightweight autoregressive TTS system that achieves competitive performance through minimalist architecture and rigorous data engineering. PilotTTS is trained on only 200K hours of data processed entirely with open-source tools. Specifically, our contributions are: (1) a reproducible multi-stage data processing pipeline covering quality a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27258","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.27258/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.27258","created_at":"2026-05-27T02:06:08.763261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27258v1","created_at":"2026-05-27T02:06:08.763261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27258","created_at":"2026-05-27T02:06:08.763261+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVYG2IAEO4G6","created_at":"2026-05-27T02:06:08.763261+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVYG2IAEO4G6DMA2","created_at":"2026-05-27T02:06:08.763261+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVYG2IAE","created_at":"2026-05-27T02:06:08.763261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF","json":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF.json","graph_json":"https://pith.science/api/pith-number/JVYG2IAEO4G6DMA2BTTMECR6CF/graph.json","events_json":"https://pith.science/api/pith-number/JVYG2IAEO4G6DMA2BTTMECR6CF/events.json","paper":"https://pith.science/paper/JVYG2IAE"},"agent_actions":{"view_html":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF","download_json":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF.json","view_paper":"https://pith.science/paper/JVYG2IAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27258&json=true","fetch_graph":"https://pith.science/api/pith-number/JVYG2IAEO4G6DMA2BTTMECR6CF/graph.json","fetch_events":"https://pith.science/api/pith-number/JVYG2IAEO4G6DMA2BTTMECR6CF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF/action/storage_attestation","attest_author":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF/action/author_attestation","sign_citation":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF/action/citation_signature","submit_replication":"https://pith.science/pith/JVYG2IAEO4G6DMA2BTTMECR6CF/action/replication_record"}},"created_at":"2026-05-27T02:06:08.763261+00:00","updated_at":"2026-05-27T02:06:08.763261+00:00"}