{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UHXRPL73NUIALDP2PPTNM4SHXQ","short_pith_number":"pith:UHXRPL73","canonical_record":{"source":{"id":"2306.02579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:10:04Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a7fe0a22baf9676905aa843f0b8f4841ea45164954cac5c591f47828d801c444","abstract_canon_sha256":"c0315067173c6824c67c01b1b10e57a2d3e72c021a7e0197a2acefed814851d3"},"schema_version":"1.0"},"canonical_sha256":"a1ef17affb6d10058dfa7be6d67247bc0785d1e893b5c82a591bf5f749133769","source":{"kind":"arxiv","id":"2306.02579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02579","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02579v1","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02579","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"UHXRPL73NUIA","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"UHXRPL73NUIALDP2","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"UHXRPL73","created_at":"2026-07-05T06:17:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UHXRPL73NUIALDP2PPTNM4SHXQ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:10:04Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a7fe0a22baf9676905aa843f0b8f4841ea45164954cac5c591f47828d801c444","abstract_canon_sha256":"c0315067173c6824c67c01b1b10e57a2d3e72c021a7e0197a2acefed814851d3"},"schema_version":"1.0"},"canonical_sha256":"a1ef17affb6d10058dfa7be6d67247bc0785d1e893b5c82a591bf5f749133769","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:18.905636Z","signature_b64":"sz+Ul/M+/RJ1sxGxgrQAWLhi3GreckuwDY+tPqO6mqIYmwEM/rjpr1VD329Q0nQlBiv9FG0E/amuplT8kcbNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1ef17affb6d10058dfa7be6d67247bc0785d1e893b5c82a591bf5f749133769","last_reissued_at":"2026-07-05T06:17:18.905153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:18.905153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02579","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RS8tndg4FBbmzrcetCqGnuEFGBvpMzAQzATTg/iIWDnEQwis2X5oQ86/JG+wwDxUDzpWsuAqcq3ikn4+TWsuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:03:36.166054Z"},"content_sha256":"cc870523c95a57086c2a8390ced39c0b5217d24025df657b88af43386d39c245","schema_version":"1.0","event_id":"sha256:cc870523c95a57086c2a8390ced39c0b5217d24025df657b88af43386d39c245"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UHXRPL73NUIALDP2PPTNM4SHXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hoyeon Lee, Hyun-Wook Yoon, Jae-Min Kim, Jong-Hwan Kim","submitted_at":"2023-06-05T04:10:04Z","abstract_excerpt":"Phrase break prediction is a crucial task for improving the prosody naturalness of a text-to-speech (TTS) system. However, most proposed phrase break prediction models are monolingual, trained exclusively on a large amount of labeled data. In this paper, we address this issue for low-resource languages with limited labeled data using cross-lingual transfer. We investigate the effectiveness of zero-shot and few-shot cross-lingual transfer for phrase break prediction using a pre-trained multilingual language model. We use manually collected datasets in four Indo-European languages: one high-reso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02579","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/2306.02579/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mq0xi180vBfqE44pCRMqBD4sYgiBKgN84zoIXh6kjkKEVrNA4Ir5oHaKzoQjoj8Q55YlyHWuZsMThuN20UmPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T01:03:36.166459Z"},"content_sha256":"6a4ecbedce048bd146f22ed64cc9228c888ba15d885c3d01d2145cfc648e6d03","schema_version":"1.0","event_id":"sha256:6a4ecbedce048bd146f22ed64cc9228c888ba15d885c3d01d2145cfc648e6d03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHXRPL73NUIALDP2PPTNM4SHXQ/bundle.json","state_url":"https://pith.science/pith/UHXRPL73NUIALDP2PPTNM4SHXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHXRPL73NUIALDP2PPTNM4SHXQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T01:03:36Z","links":{"resolver":"https://pith.science/pith/UHXRPL73NUIALDP2PPTNM4SHXQ","bundle":"https://pith.science/pith/UHXRPL73NUIALDP2PPTNM4SHXQ/bundle.json","state":"https://pith.science/pith/UHXRPL73NUIALDP2PPTNM4SHXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHXRPL73NUIALDP2PPTNM4SHXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UHXRPL73NUIALDP2PPTNM4SHXQ","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":"c0315067173c6824c67c01b1b10e57a2d3e72c021a7e0197a2acefed814851d3","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:10:04Z","title_canon_sha256":"a7fe0a22baf9676905aa843f0b8f4841ea45164954cac5c591f47828d801c444"},"schema_version":"1.0","source":{"id":"2306.02579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02579","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02579v1","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02579","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"UHXRPL73NUIA","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"UHXRPL73NUIALDP2","created_at":"2026-07-05T06:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"UHXRPL73","created_at":"2026-07-05T06:17:18Z"}],"graph_snapshots":[{"event_id":"sha256:6a4ecbedce048bd146f22ed64cc9228c888ba15d885c3d01d2145cfc648e6d03","target":"graph","created_at":"2026-07-05T06:17:18Z","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/2306.02579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Phrase break prediction is a crucial task for improving the prosody naturalness of a text-to-speech (TTS) system. However, most proposed phrase break prediction models are monolingual, trained exclusively on a large amount of labeled data. In this paper, we address this issue for low-resource languages with limited labeled data using cross-lingual transfer. We investigate the effectiveness of zero-shot and few-shot cross-lingual transfer for phrase break prediction using a pre-trained multilingual language model. We use manually collected datasets in four Indo-European languages: one high-reso","authors_text":"Hoyeon Lee, Hyun-Wook Yoon, Jae-Min Kim, Jong-Hwan Kim","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:10:04Z","title":"Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02579","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:cc870523c95a57086c2a8390ced39c0b5217d24025df657b88af43386d39c245","target":"record","created_at":"2026-07-05T06:17:18Z","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":"c0315067173c6824c67c01b1b10e57a2d3e72c021a7e0197a2acefed814851d3","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T04:10:04Z","title_canon_sha256":"a7fe0a22baf9676905aa843f0b8f4841ea45164954cac5c591f47828d801c444"},"schema_version":"1.0","source":{"id":"2306.02579","kind":"arxiv","version":1}},"canonical_sha256":"a1ef17affb6d10058dfa7be6d67247bc0785d1e893b5c82a591bf5f749133769","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1ef17affb6d10058dfa7be6d67247bc0785d1e893b5c82a591bf5f749133769","first_computed_at":"2026-07-05T06:17:18.905153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:18.905153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sz+Ul/M+/RJ1sxGxgrQAWLhi3GreckuwDY+tPqO6mqIYmwEM/rjpr1VD329Q0nQlBiv9FG0E/amuplT8kcbNDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:18.905636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc870523c95a57086c2a8390ced39c0b5217d24025df657b88af43386d39c245","sha256:6a4ecbedce048bd146f22ed64cc9228c888ba15d885c3d01d2145cfc648e6d03"],"state_sha256":"b155d74fa4fd24efc76f088328b9108b0c783920860356a336ace233341a05ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+XHbxXFxoNYS3N3OLBDm3OI4xMJ/xshzfiznMwMrBHeA+snhsFb/7k3emjoboXBzlCo2cKAL7ftir5Az36rAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T01:03:36.168464Z","bundle_sha256":"042bda053bd99a05222699ca32e5eabc3ad43365f231b8c5fb82bc20c49baa8e"}}