{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ROPUP36DSVR74BVTE7AIXZWAAC","short_pith_number":"pith:ROPUP36D","schema_version":"1.0","canonical_sha256":"8b9f47efc39563fe06b327c08be6c0009bd1614acc2025137dd067021d826dff","source":{"kind":"arxiv","id":"2403.08229","version":2},"attestation_state":"computed","paper":{"title":"Boosting Disfluency Detection with Large Language Model as Disfluency Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Sun, Jiayan Guo, Yan Zhang, Zhenrong Cheng","submitted_at":"2024-03-13T04:14:33Z","abstract_excerpt":"Current disfluency detection methods heavily rely on costly and scarce human-annotated data. To tackle this issue, some approaches employ heuristic or statistical features to generate disfluent sentences, partially improving detection performance. However, these sentences often deviate from real-life scenarios, constraining overall model enhancement. In this study, we propose a lightweight data augmentation approach for disfluency detection, utilizing the superior generative and semantic understanding capabilities of large language model (LLM) to generate disfluent sentences as augmentation da"},"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":"2403.08229","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T04:14:33Z","cross_cats_sorted":[],"title_canon_sha256":"ffb442a9d256402531614e3c0bc5445e64b4fa01c931446777a9e3f75d219ff4","abstract_canon_sha256":"6293a63dda572d17624f7e8f4083dca25483a447b3fa4db4e724ade7b6bdfed8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:30.274420Z","signature_b64":"ewyZV2r+7SxzTNl6TiYcefmtVPrRBOmzzoVZnv75YgEsvPMcoydLUfofsADPfJKYCz6pxxTMwhOilkA+HqMxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b9f47efc39563fe06b327c08be6c0009bd1614acc2025137dd067021d826dff","last_reissued_at":"2026-07-05T08:52:30.273941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:30.273941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Disfluency Detection with Large Language Model as Disfluency Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Sun, Jiayan Guo, Yan Zhang, Zhenrong Cheng","submitted_at":"2024-03-13T04:14:33Z","abstract_excerpt":"Current disfluency detection methods heavily rely on costly and scarce human-annotated data. To tackle this issue, some approaches employ heuristic or statistical features to generate disfluent sentences, partially improving detection performance. However, these sentences often deviate from real-life scenarios, constraining overall model enhancement. In this study, we propose a lightweight data augmentation approach for disfluency detection, utilizing the superior generative and semantic understanding capabilities of large language model (LLM) to generate disfluent sentences as augmentation da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08229","kind":"arxiv","version":2},"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/2403.08229/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":"2403.08229","created_at":"2026-07-05T08:52:30.273989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08229v2","created_at":"2026-07-05T08:52:30.273989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08229","created_at":"2026-07-05T08:52:30.273989+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROPUP36DSVR7","created_at":"2026-07-05T08:52:30.273989+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROPUP36DSVR74BVT","created_at":"2026-07-05T08:52:30.273989+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROPUP36D","created_at":"2026-07-05T08:52:30.273989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12242","citing_title":"Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC","json":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC.json","graph_json":"https://pith.science/api/pith-number/ROPUP36DSVR74BVTE7AIXZWAAC/graph.json","events_json":"https://pith.science/api/pith-number/ROPUP36DSVR74BVTE7AIXZWAAC/events.json","paper":"https://pith.science/paper/ROPUP36D"},"agent_actions":{"view_html":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC","download_json":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC.json","view_paper":"https://pith.science/paper/ROPUP36D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08229&json=true","fetch_graph":"https://pith.science/api/pith-number/ROPUP36DSVR74BVTE7AIXZWAAC/graph.json","fetch_events":"https://pith.science/api/pith-number/ROPUP36DSVR74BVTE7AIXZWAAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC/action/storage_attestation","attest_author":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC/action/author_attestation","sign_citation":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC/action/citation_signature","submit_replication":"https://pith.science/pith/ROPUP36DSVR74BVTE7AIXZWAAC/action/replication_record"}},"created_at":"2026-07-05T08:52:30.273989+00:00","updated_at":"2026-07-05T08:52:30.273989+00:00"}