{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XKC4HHE4ARHIOAE6A6BHRQVTZQ","short_pith_number":"pith:XKC4HHE4","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"},"canonical_sha256":"ba85c39c9c044e87009e078278c2b3cc0fb14fe6c8f25676176d6042f8835488","source":{"kind":"arxiv","id":"1908.05378","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05378","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05378v2","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05378","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"XKC4HHE4ARHI","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"XKC4HHE4ARHIOAE6","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"XKC4HHE4","created_at":"2026-07-05T00:54:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XKC4HHE4ARHIOAE6A6BHRQVTZQ","target":"record","payload":{"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"},"canonical_sha256":"ba85c39c9c044e87009e078278c2b3cc0fb14fe6c8f25676176d6042f8835488","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"},"source_kind":"arxiv","source_id":"1908.05378","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x3KJT7UuNGuAmWSkN/dVPL2XUXHhtTdH5EaBxtOWlgM3blMfQjUkSwVLREqCGbQ1ylKdtvg42qK0xE/6RlGuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:30:22.459322Z"},"content_sha256":"4b3d3fdacc330b3717fbf01768777df5e685d78c0056506c4b2524e7dc7dd2da","schema_version":"1.0","event_id":"sha256:4b3d3fdacc330b3717fbf01768777df5e685d78c0056506c4b2524e7dc7dd2da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XKC4HHE4ARHIOAE6A6BHRQVTZQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7aeolz8tWyH4ByH0gaBdGoeRkNEpo8Ux06LWJ2Y9VPHxvoTRC7vc+zVQin29UWcuAaT3erOgitffUMnVvhTCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:30:22.460097Z"},"content_sha256":"96c6b4b9f742a7911db20a4193286ba1947035cbe11280d7ed492e61bf23d71b","schema_version":"1.0","event_id":"sha256:96c6b4b9f742a7911db20a4193286ba1947035cbe11280d7ed492e61bf23d71b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/bundle.json","state_url":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/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":"2026-08-16T06:30:22Z","links":{"resolver":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ","bundle":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/bundle.json","state":"https://pith.science/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKC4HHE4ARHIOAE6A6BHRQVTZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XKC4HHE4ARHIOAE6A6BHRQVTZQ","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":"7c4cf45189c48998635eab90e6132fa2a18c1a4c5647d17353b1453b40d1407d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T00:22:38Z","title_canon_sha256":"8b0f0bddd6a5936ce3982caecac3afb5efd2726847bf28a68fa734deedb24685"},"schema_version":"1.0","source":{"id":"1908.05378","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05378","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05378v2","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05378","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"XKC4HHE4ARHI","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"XKC4HHE4ARHIOAE6","created_at":"2026-07-05T00:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"XKC4HHE4","created_at":"2026-07-05T00:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:96c6b4b9f742a7911db20a4193286ba1947035cbe11280d7ed492e61bf23d71b","target":"graph","created_at":"2026-07-05T00:54:02Z","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/1908.05378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Pengda Qin, Qi Liu, Shaolei Wang, Ting Liu, Wanxiang Che, William Yang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T00:22:38Z","title":"Multi-Task Self-Supervised Learning for Disfluency Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05378","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":"sha256:4b3d3fdacc330b3717fbf01768777df5e685d78c0056506c4b2524e7dc7dd2da","target":"record","created_at":"2026-07-05T00:54:02Z","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":"7c4cf45189c48998635eab90e6132fa2a18c1a4c5647d17353b1453b40d1407d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T00:22:38Z","title_canon_sha256":"8b0f0bddd6a5936ce3982caecac3afb5efd2726847bf28a68fa734deedb24685"},"schema_version":"1.0","source":{"id":"1908.05378","kind":"arxiv","version":2}},"canonical_sha256":"ba85c39c9c044e87009e078278c2b3cc0fb14fe6c8f25676176d6042f8835488","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba85c39c9c044e87009e078278c2b3cc0fb14fe6c8f25676176d6042f8835488","first_computed_at":"2026-07-05T00:54:02.036075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:54:02.036075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BJrPExSvVAS+8AiCT/XGmqBPQtF1JINTppy56y94B9FDLzr88cCwF1owXCprUE8uhG0FhoHPAL/6OMJQC+ePDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:54:02.036485Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05378","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b3d3fdacc330b3717fbf01768777df5e685d78c0056506c4b2524e7dc7dd2da","sha256:96c6b4b9f742a7911db20a4193286ba1947035cbe11280d7ed492e61bf23d71b"],"state_sha256":"69d8b8da6df52b6f98bd4d9377ee97f844e707407776e52a2568ad3e892dfb8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1P7AziUAMMwkUk9XdwyA8nRvSnhiPnC6HkUpBAv/CF6ALzIj7m45VVmyppCOrGk9vSMvRpP6kyWeC/bulF3MBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T06:30:22.467278Z","bundle_sha256":"1279157f6b407aed3f503e68df2170ad434f90323ea2c67710418800a4cc826e"}}