{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ASQ6MVEYZXQMFB5YVK435BEX54","short_pith_number":"pith:ASQ6MVEY","schema_version":"1.0","canonical_sha256":"04a1e65498cde0c287b8aab9be8497ef07e47f1cf0a70a10924883cf764098e7","source":{"kind":"arxiv","id":"2607.06054","version":1},"attestation_state":"computed","paper":{"title":"BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Bo-Xuan Zheng, Cheng-Chieh Huang, Cheng-Han Chang, Ho Lam Chung, Hung-yi Lee, Jung-Ching Chen, Lok-Lam Ieong, Ting-Lin Hsiao, Yi-Hsin Chung, Yu-Cheng Lee, Yu-Kai Guo","submitted_at":"2026-07-07T09:31:19Z","abstract_excerpt":"Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their accent defaults to other Mandarin variants, their tokenizers over-segment common Taiwanese text, and their pronunciation degrades at code-switching boundaries where Chinese and English alternate within one utterance. These problems share one root: the text side lacks adaptation to the Taiwanese context. We address the text side from the bottom up. PangolinTokenizer, a byte-level BPE tokenizer trained on Taiwan-context data, reaches the lowest token rate (0.485 tokens/character) with the smallest vocabulary among nine tok"},"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":"2607.06054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-07T09:31:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc023e4d2b5987d53af5d4644aa515c18cb727364a6fc68caea87d2561e590c6","abstract_canon_sha256":"11eada4a519313a978c3407527b541f30d92d13294f7642a405b1a86925513e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:55.172010Z","signature_b64":"Jqk3Y+4vFcPPN2nQqPCyzaHozcqnNlZA1rOkjNfbZZ5Dr0WFc9d0WTp44dZscGFUAsoJagZv704qJKRLZlwaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04a1e65498cde0c287b8aab9be8497ef07e47f1cf0a70a10924883cf764098e7","last_reissued_at":"2026-07-08T01:18:55.171555Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:55.171555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Bo-Xuan Zheng, Cheng-Chieh Huang, Cheng-Han Chang, Ho Lam Chung, Hung-yi Lee, Jung-Ching Chen, Lok-Lam Ieong, Ting-Lin Hsiao, Yi-Hsin Chung, Yu-Cheng Lee, Yu-Kai Guo","submitted_at":"2026-07-07T09:31:19Z","abstract_excerpt":"Off-the-shelf TTS systems are poorly adapted to Taiwanese Mandarin. Their accent defaults to other Mandarin variants, their tokenizers over-segment common Taiwanese text, and their pronunciation degrades at code-switching boundaries where Chinese and English alternate within one utterance. These problems share one root: the text side lacks adaptation to the Taiwanese context. We address the text side from the bottom up. PangolinTokenizer, a byte-level BPE tokenizer trained on Taiwan-context data, reaches the lowest token rate (0.485 tokens/character) with the smallest vocabulary among nine tok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06054","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/2607.06054/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":"2607.06054","created_at":"2026-07-08T01:18:55.171629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06054v1","created_at":"2026-07-08T01:18:55.171629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06054","created_at":"2026-07-08T01:18:55.171629+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASQ6MVEYZXQM","created_at":"2026-07-08T01:18:55.171629+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASQ6MVEYZXQMFB5Y","created_at":"2026-07-08T01:18:55.171629+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASQ6MVEY","created_at":"2026-07-08T01:18:55.171629+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/ASQ6MVEYZXQMFB5YVK435BEX54","json":"https://pith.science/pith/ASQ6MVEYZXQMFB5YVK435BEX54.json","graph_json":"https://pith.science/api/pith-number/ASQ6MVEYZXQMFB5YVK435BEX54/graph.json","events_json":"https://pith.science/api/pith-number/ASQ6MVEYZXQMFB5YVK435BEX54/events.json","paper":"https://pith.science/paper/ASQ6MVEY"},"agent_actions":{"view_html":"https://pith.science/pith/ASQ6MVEYZXQMFB5YVK435BEX54","download_json":"https://pith.science/pith/ASQ6MVEYZXQMFB5YVK435BEX54.json","view_paper":"https://pith.science/paper/ASQ6MVEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06054&json=true","fetch_graph":"https://pith.science/api/pith-number/ASQ6MVEYZXQMFB5YVK435BEX54/graph.json","fetch_events":"https://pith.science/api/pith-number/ASQ6MVEYZXQMFB5YVK435BEX54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASQ6MVEYZXQMFB5YVK435BEX54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASQ6MVEYZXQMFB5YVK435BEX54/action/storage_attestation","attest_author":"https://pith.science/pith/ASQ6MVEYZXQMFB5YVK435BEX54/action/author_attestation","sign_citation":"https://pith.science/pith/ASQ6MVEYZXQMFB5YVK435BEX54/action/citation_signature","submit_replication":"https://pith.science/pith/ASQ6MVEYZXQMFB5YVK435BEX54/action/replication_record"}},"created_at":"2026-07-08T01:18:55.171629+00:00","updated_at":"2026-07-08T01:18:55.171629+00:00"}