{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RQTOO3JLP7XAC2G4LDD2LCGZJB","short_pith_number":"pith:RQTOO3JL","schema_version":"1.0","canonical_sha256":"8c26e76d2b7fee0168dc58c7a588d9487bdcd2fd3e80072ee7d58740adbdb341","source":{"kind":"arxiv","id":"1904.06652","version":1},"attestation_state":"computed","paper":{"title":"Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jimmy Lin, Kun Xiong, Luchen Tan, Ming Li, Wei Yang, Yuqing Xie","submitted_at":"2019-04-14T08:17:06Z","abstract_excerpt":"Recently, a simple combination of passage retrieval using off-the-shelf IR techniques and a BERT reader was found to be very effective for question answering directly on Wikipedia, yielding a large improvement over the previous state of the art on a standard benchmark dataset. In this paper, we present a data augmentation technique using distant supervision that exploits positive as well as negative examples. We apply a stage-wise approach to fine tuning BERT on multiple datasets, starting with data that is \"furthest\" from the test data and ending with the \"closest\". Experimental results show "},"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":"1904.06652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-14T08:17:06Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c5e9458961503065c28233b3b4cfb72cab4d454051dbdbcbf60de87aaeb35e03","abstract_canon_sha256":"32332322138fe929d21842bcad9203e0a4a9a81169ce022e5efea97d8f7b0384"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:36.630552Z","signature_b64":"iOlSRTrptx4uDJh5qnS8wOFoy39Xlm8mk2BNS66SHsMnVlr2mh2KMWCWAcjJ9d78WfP8WblSMzjgZvkRpGoGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c26e76d2b7fee0168dc58c7a588d9487bdcd2fd3e80072ee7d58740adbdb341","last_reissued_at":"2026-05-17T23:48:36.629974Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:36.629974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jimmy Lin, Kun Xiong, Luchen Tan, Ming Li, Wei Yang, Yuqing Xie","submitted_at":"2019-04-14T08:17:06Z","abstract_excerpt":"Recently, a simple combination of passage retrieval using off-the-shelf IR techniques and a BERT reader was found to be very effective for question answering directly on Wikipedia, yielding a large improvement over the previous state of the art on a standard benchmark dataset. In this paper, we present a data augmentation technique using distant supervision that exploits positive as well as negative examples. We apply a stage-wise approach to fine tuning BERT on multiple datasets, starting with data that is \"furthest\" from the test data and ending with the \"closest\". Experimental results show "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06652","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":""},"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":"1904.06652","created_at":"2026-05-17T23:48:36.630075+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06652v1","created_at":"2026-05-17T23:48:36.630075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06652","created_at":"2026-05-17T23:48:36.630075+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQTOO3JLP7XA","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQTOO3JLP7XAC2G4","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQTOO3JL","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2004.04906","citing_title":"Dense Passage Retrieval for Open-Domain Question Answering","ref_index":112,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB","json":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB.json","graph_json":"https://pith.science/api/pith-number/RQTOO3JLP7XAC2G4LDD2LCGZJB/graph.json","events_json":"https://pith.science/api/pith-number/RQTOO3JLP7XAC2G4LDD2LCGZJB/events.json","paper":"https://pith.science/paper/RQTOO3JL"},"agent_actions":{"view_html":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB","download_json":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB.json","view_paper":"https://pith.science/paper/RQTOO3JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06652&json=true","fetch_graph":"https://pith.science/api/pith-number/RQTOO3JLP7XAC2G4LDD2LCGZJB/graph.json","fetch_events":"https://pith.science/api/pith-number/RQTOO3JLP7XAC2G4LDD2LCGZJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB/action/storage_attestation","attest_author":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB/action/author_attestation","sign_citation":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB/action/citation_signature","submit_replication":"https://pith.science/pith/RQTOO3JLP7XAC2G4LDD2LCGZJB/action/replication_record"}},"created_at":"2026-05-17T23:48:36.630075+00:00","updated_at":"2026-05-17T23:48:36.630075+00:00"}