{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CVGUOLECDFIJQ6DOKAO6JNZIYJ","short_pith_number":"pith:CVGUOLEC","schema_version":"1.0","canonical_sha256":"154d472c82195098786e501de4b728c26240af01f62097fa3255615a1d77b249","source":{"kind":"arxiv","id":"2507.18044","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Data Generation for Phrase Break Prediction with Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hoyeon Lee, Jong-Hwan Kim, Sejung Son, Ye-Eun Kang","submitted_at":"2025-07-24T02:45:03Z","abstract_excerpt":"Current approaches to phrase break prediction address crucial prosodic aspects of text-to-speech systems but heavily rely on vast human annotations from audio or text, incurring significant manual effort and cost. Inherent variability in the speech domain, driven by phonetic factors, further complicates acquiring consistent, high-quality data. Recently, large language models (LLMs) have shown success in addressing data challenges in NLP by generating tailored synthetic data while reducing manual annotation needs. Motivated by this, we explore leveraging LLM to generate synthetic phrase break 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":"2507.18044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T02:45:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b68d97fd1c76bdb89c3361a921976d9a0c0f9d1bb023c5d84de4c23896a659a8","abstract_canon_sha256":"46fb9d16eea7858068e081bae8334d37d1b75cfe662b018cad47b0a3966978f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:40.044790Z","signature_b64":"DoQ06JhSRjpnT3tb8ob9w4qWhkirWHEGnx8z7SRYvNMxNdDgxGwsnLYKFMH5EXWUmBZVVIH8A0bT89XaPxbiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"154d472c82195098786e501de4b728c26240af01f62097fa3255615a1d77b249","last_reissued_at":"2026-07-05T11:42:40.044298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:40.044298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Data Generation for Phrase Break Prediction with Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hoyeon Lee, Jong-Hwan Kim, Sejung Son, Ye-Eun Kang","submitted_at":"2025-07-24T02:45:03Z","abstract_excerpt":"Current approaches to phrase break prediction address crucial prosodic aspects of text-to-speech systems but heavily rely on vast human annotations from audio or text, incurring significant manual effort and cost. Inherent variability in the speech domain, driven by phonetic factors, further complicates acquiring consistent, high-quality data. Recently, large language models (LLMs) have shown success in addressing data challenges in NLP by generating tailored synthetic data while reducing manual annotation needs. Motivated by this, we explore leveraging LLM to generate synthetic phrase break a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18044","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/2507.18044/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":"2507.18044","created_at":"2026-07-05T11:42:40.044368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18044v1","created_at":"2026-07-05T11:42:40.044368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18044","created_at":"2026-07-05T11:42:40.044368+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVGUOLECDFIJ","created_at":"2026-07-05T11:42:40.044368+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVGUOLECDFIJQ6DO","created_at":"2026-07-05T11:42:40.044368+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVGUOLEC","created_at":"2026-07-05T11:42:40.044368+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/CVGUOLECDFIJQ6DOKAO6JNZIYJ","json":"https://pith.science/pith/CVGUOLECDFIJQ6DOKAO6JNZIYJ.json","graph_json":"https://pith.science/api/pith-number/CVGUOLECDFIJQ6DOKAO6JNZIYJ/graph.json","events_json":"https://pith.science/api/pith-number/CVGUOLECDFIJQ6DOKAO6JNZIYJ/events.json","paper":"https://pith.science/paper/CVGUOLEC"},"agent_actions":{"view_html":"https://pith.science/pith/CVGUOLECDFIJQ6DOKAO6JNZIYJ","download_json":"https://pith.science/pith/CVGUOLECDFIJQ6DOKAO6JNZIYJ.json","view_paper":"https://pith.science/paper/CVGUOLEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18044&json=true","fetch_graph":"https://pith.science/api/pith-number/CVGUOLECDFIJQ6DOKAO6JNZIYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CVGUOLECDFIJQ6DOKAO6JNZIYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVGUOLECDFIJQ6DOKAO6JNZIYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVGUOLECDFIJQ6DOKAO6JNZIYJ/action/storage_attestation","attest_author":"https://pith.science/pith/CVGUOLECDFIJQ6DOKAO6JNZIYJ/action/author_attestation","sign_citation":"https://pith.science/pith/CVGUOLECDFIJQ6DOKAO6JNZIYJ/action/citation_signature","submit_replication":"https://pith.science/pith/CVGUOLECDFIJQ6DOKAO6JNZIYJ/action/replication_record"}},"created_at":"2026-07-05T11:42:40.044368+00:00","updated_at":"2026-07-05T11:42:40.044368+00:00"}