{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XKC4HHE4ARHIOAE6A6BHRQVTZQ","short_pith_number":"pith:XKC4HHE4","schema_version":"1.0","canonical_sha256":"ba85c39c9c044e87009e078278c2b3cc0fb14fe6c8f25676176d6042f8835488","source":{"kind":"arxiv","id":"1908.05378","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Self-Supervised Learning for Disfluency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pengda Qin, Qi Liu, Shaolei Wang, Ting Liu, Wanxiang Che, William Yang Wang","submitted_at":"2019-08-15T00:22:38Z","abstract_excerpt":"Most existing approaches to disfluency detection heavily rely on human-annotated data, which is expensive to obtain in practice. To tackle the training data bottleneck, we investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled news data, and propose two self-supervised pre-training tasks: (i) tagging task to detect the added noisy words. (ii) sentence classification to distinguish original sentences from g"},"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":"1908.05378","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T00:22:38Z","cross_cats_sorted":[],"title_canon_sha256":"8b0f0bddd6a5936ce3982caecac3afb5efd2726847bf28a68fa734deedb24685","abstract_canon_sha256":"7c4cf45189c48998635eab90e6132fa2a18c1a4c5647d17353b1453b40d1407d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:02.036485Z","signature_b64":"BJrPExSvVAS+8AiCT/XGmqBPQtF1JINTppy56y94B9FDLzr88cCwF1owXCprUE8uhG0FhoHPAL/6OMJQC+ePDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba85c39c9c044e87009e078278c2b3cc0fb14fe6c8f25676176d6042f8835488","last_reissued_at":"2026-07-05T00:54:02.036075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:02.036075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Self-Supervised Learning for Disfluency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pengda Qin, Qi Liu, Shaolei Wang, Ting Liu, Wanxiang Che, William Yang Wang","submitted_at":"2019-08-15T00:22:38Z","abstract_excerpt":"Most existing approaches to disfluency detection heavily rely on human-annotated data, which is expensive to obtain in practice. To tackle the training data bottleneck, we investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled news data, and propose two self-supervised pre-training tasks: (i) tagging task to detect the added noisy words. (ii) sentence classification to distinguish original sentences from g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05378","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/1908.05378/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":"1908.05378","created_at":"2026-07-05T00:54:02.036139+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05378v2","created_at":"2026-07-05T00:54:02.036139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05378","created_at":"2026-07-05T00:54:02.036139+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKC4HHE4ARHI","created_at":"2026-07-05T00:54:02.036139+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKC4HHE4ARHIOAE6","created_at":"2026-07-05T00:54:02.036139+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKC4HHE4","created_at":"2026-07-05T00:54:02.036139+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/XKC4HHE4ARHIOAE6A6BHRQVTZQ","json":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ.json","graph_json":"https://pith.science/api/pith-number/XKC4HHE4ARHIOAE6A6BHRQVTZQ/graph.json","events_json":"https://pith.science/api/pith-number/XKC4HHE4ARHIOAE6A6BHRQVTZQ/events.json","paper":"https://pith.science/paper/XKC4HHE4"},"agent_actions":{"view_html":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ","download_json":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ.json","view_paper":"https://pith.science/paper/XKC4HHE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05378&json=true","fetch_graph":"https://pith.science/api/pith-number/XKC4HHE4ARHIOAE6A6BHRQVTZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XKC4HHE4ARHIOAE6A6BHRQVTZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/action/storage_attestation","attest_author":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/action/author_attestation","sign_citation":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/action/citation_signature","submit_replication":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/action/replication_record"}},"created_at":"2026-07-05T00:54:02.036139+00:00","updated_at":"2026-07-05T00:54:02.036139+00:00"}