{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ROPUP36DSVR74BVTE7AIXZWAAC","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":"6293a63dda572d17624f7e8f4083dca25483a447b3fa4db4e724ade7b6bdfed8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T04:14:33Z","title_canon_sha256":"ffb442a9d256402531614e3c0bc5445e64b4fa01c931446777a9e3f75d219ff4"},"schema_version":"1.0","source":{"id":"2403.08229","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08229","created_at":"2026-07-05T08:52:30Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08229v2","created_at":"2026-07-05T08:52:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08229","created_at":"2026-07-05T08:52:30Z"},{"alias_kind":"pith_short_12","alias_value":"ROPUP36DSVR7","created_at":"2026-07-05T08:52:30Z"},{"alias_kind":"pith_short_16","alias_value":"ROPUP36DSVR74BVT","created_at":"2026-07-05T08:52:30Z"},{"alias_kind":"pith_short_8","alias_value":"ROPUP36D","created_at":"2026-07-05T08:52:30Z"}],"graph_snapshots":[{"event_id":"sha256:a73a550519bf365d7d026f037e377fe521b4cfe2f4b7a99f7512865dd59e3695","target":"graph","created_at":"2026-07-05T08:52:30Z","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/2403.08229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hao Sun, Jiayan Guo, Yan Zhang, Zhenrong Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T04:14:33Z","title":"Boosting Disfluency Detection with Large Language Model as Disfluency Generator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08229","kind":"arxiv","version":2},"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":"sha256:671664823db83cbc2b705bbb8bcd4964f1016c44a757aed2bb6206d9a6df2b9c","target":"record","created_at":"2026-07-05T08:52:30Z","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":"6293a63dda572d17624f7e8f4083dca25483a447b3fa4db4e724ade7b6bdfed8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T04:14:33Z","title_canon_sha256":"ffb442a9d256402531614e3c0bc5445e64b4fa01c931446777a9e3f75d219ff4"},"schema_version":"1.0","source":{"id":"2403.08229","kind":"arxiv","version":2}},"canonical_sha256":"8b9f47efc39563fe06b327c08be6c0009bd1614acc2025137dd067021d826dff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b9f47efc39563fe06b327c08be6c0009bd1614acc2025137dd067021d826dff","first_computed_at":"2026-07-05T08:52:30.273941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:30.273941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ewyZV2r+7SxzTNl6TiYcefmtVPrRBOmzzoVZnv75YgEsvPMcoydLUfofsADPfJKYCz6pxxTMwhOilkA+HqMxDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:30.274420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08229","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:671664823db83cbc2b705bbb8bcd4964f1016c44a757aed2bb6206d9a6df2b9c","sha256:a73a550519bf365d7d026f037e377fe521b4cfe2f4b7a99f7512865dd59e3695"],"state_sha256":"8b818a1ce3704e7066f4e808ed7fcfc2d94d7beae44be70b06110b8d89d51c46"}