{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z44PJ5EIRZQLCUE6L5GY3HCZB5","short_pith_number":"pith:Z44PJ5EI","schema_version":"1.0","canonical_sha256":"cf38f4f4888e60b1509e5f4d8d9c590f60fd313d2213ffc644e5393efc9200d5","source":{"kind":"arxiv","id":"2606.21098","version":1},"attestation_state":"computed","paper":{"title":"LLM-Based Multi-Reference Evaluation for Efficient and Robust Assessment of Phrase Break Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hawon Jeong, Hoyeon Lee, Jong-Hwan Kim, Younghan Park","submitted_at":"2026-06-19T04:56:35Z","abstract_excerpt":"Reliable evaluation of phrase break annotations is crucial, as subtle variations in prosodic boundaries directly affect the clarity and naturalness of speech. However, existing approaches exhibit major limitations: single-reference evaluation assumes a unique gold phrasing for an utterance despite multiple valid phrasings, while human judgment, though flexible, is labor-intensive and unscalable. To address these, we propose LLM-based Multi-Reference Evaluation (LMRE) for phrase break annotations that models the one-to-many nature of prosodic phrasing and generates multiple valid phrasings from"},"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":"2606.21098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T04:56:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1f280e6b77d15e68e1ae92f708abbaafaea9e7dc6eed8e98578d1bb89dd96ff","abstract_canon_sha256":"1e5cde7c7c2031a8eea788df45e0f30b839007c599678491394f23889efc16a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:29.857445Z","signature_b64":"MX+c9HArUj5IPHfuuusX62Pnmh19dq0X+qF7dmyjQ4tp38ILgPNHscPn7uufpWZJBB/4gY9bpcTArnNANT2cBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf38f4f4888e60b1509e5f4d8d9c590f60fd313d2213ffc644e5393efc9200d5","last_reissued_at":"2026-06-23T01:12:29.856968Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:29.856968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Based Multi-Reference Evaluation for Efficient and Robust Assessment of Phrase Break Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hawon Jeong, Hoyeon Lee, Jong-Hwan Kim, Younghan Park","submitted_at":"2026-06-19T04:56:35Z","abstract_excerpt":"Reliable evaluation of phrase break annotations is crucial, as subtle variations in prosodic boundaries directly affect the clarity and naturalness of speech. However, existing approaches exhibit major limitations: single-reference evaluation assumes a unique gold phrasing for an utterance despite multiple valid phrasings, while human judgment, though flexible, is labor-intensive and unscalable. To address these, we propose LLM-based Multi-Reference Evaluation (LMRE) for phrase break annotations that models the one-to-many nature of prosodic phrasing and generates multiple valid phrasings from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21098","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/2606.21098/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":"2606.21098","created_at":"2026-06-23T01:12:29.857046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21098v1","created_at":"2026-06-23T01:12:29.857046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21098","created_at":"2026-06-23T01:12:29.857046+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z44PJ5EIRZQL","created_at":"2026-06-23T01:12:29.857046+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z44PJ5EIRZQLCUE6","created_at":"2026-06-23T01:12:29.857046+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z44PJ5EI","created_at":"2026-06-23T01:12:29.857046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.21098","citing_title":"LLM-Based Multi-Reference Evaluation for Efficient and Robust Assessment of Phrase Break Annotations","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5","json":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5.json","graph_json":"https://pith.science/api/pith-number/Z44PJ5EIRZQLCUE6L5GY3HCZB5/graph.json","events_json":"https://pith.science/api/pith-number/Z44PJ5EIRZQLCUE6L5GY3HCZB5/events.json","paper":"https://pith.science/paper/Z44PJ5EI"},"agent_actions":{"view_html":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5","download_json":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5.json","view_paper":"https://pith.science/paper/Z44PJ5EI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21098&json=true","fetch_graph":"https://pith.science/api/pith-number/Z44PJ5EIRZQLCUE6L5GY3HCZB5/graph.json","fetch_events":"https://pith.science/api/pith-number/Z44PJ5EIRZQLCUE6L5GY3HCZB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5/action/storage_attestation","attest_author":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5/action/author_attestation","sign_citation":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5/action/citation_signature","submit_replication":"https://pith.science/pith/Z44PJ5EIRZQLCUE6L5GY3HCZB5/action/replication_record"}},"created_at":"2026-06-23T01:12:29.857046+00:00","updated_at":"2026-06-23T01:12:29.857046+00:00"}