{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ASQ6MVEYZXQMFB5YVK435BEX54","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":"11eada4a519313a978c3407527b541f30d92d13294f7642a405b1a86925513e8","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-07T09:31:19Z","title_canon_sha256":"bc023e4d2b5987d53af5d4644aa515c18cb727364a6fc68caea87d2561e590c6"},"schema_version":"1.0","source":{"id":"2607.06054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06054","created_at":"2026-07-08T01:18:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06054v1","created_at":"2026-07-08T01:18:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06054","created_at":"2026-07-08T01:18:55Z"},{"alias_kind":"pith_short_12","alias_value":"ASQ6MVEYZXQM","created_at":"2026-07-08T01:18:55Z"},{"alias_kind":"pith_short_16","alias_value":"ASQ6MVEYZXQMFB5Y","created_at":"2026-07-08T01:18:55Z"},{"alias_kind":"pith_short_8","alias_value":"ASQ6MVEY","created_at":"2026-07-08T01:18:55Z"}],"graph_snapshots":[{"event_id":"sha256:47c38c98bb09e4e9adcd7db445a8d51bef25082eaf4bf81997df0c5e7fd4d098","target":"graph","created_at":"2026-07-08T01:18:55Z","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/2607.06054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-07T09:31:19Z","title":"BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06054","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":"sha256:98fcc76b3fb7c3618470b2c801f17eea94241714b7a4c78bd781062713a2d27f","target":"record","created_at":"2026-07-08T01:18:55Z","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":"11eada4a519313a978c3407527b541f30d92d13294f7642a405b1a86925513e8","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-07T09:31:19Z","title_canon_sha256":"bc023e4d2b5987d53af5d4644aa515c18cb727364a6fc68caea87d2561e590c6"},"schema_version":"1.0","source":{"id":"2607.06054","kind":"arxiv","version":1}},"canonical_sha256":"04a1e65498cde0c287b8aab9be8497ef07e47f1cf0a70a10924883cf764098e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04a1e65498cde0c287b8aab9be8497ef07e47f1cf0a70a10924883cf764098e7","first_computed_at":"2026-07-08T01:18:55.171555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:55.171555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jqk3Y+4vFcPPN2nQqPCyzaHozcqnNlZA1rOkjNfbZZ5Dr0WFc9d0WTp44dZscGFUAsoJagZv704qJKRLZlwaBg==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:55.172010Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98fcc76b3fb7c3618470b2c801f17eea94241714b7a4c78bd781062713a2d27f","sha256:47c38c98bb09e4e9adcd7db445a8d51bef25082eaf4bf81997df0c5e7fd4d098"],"state_sha256":"ceb312047ba22cfaa86316eab5fdb8c365bf3f28abf21ef5acd58bb26849dde0"}