{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3PDBQCOG4BSR3BEEFEC2QZQCAC","short_pith_number":"pith:3PDBQCOG","schema_version":"1.0","canonical_sha256":"dbc61809c6e0651d84842905a866020094080759853916233b772761f5cd211d","source":{"kind":"arxiv","id":"1809.00732","version":1},"attestation_state":"computed","paper":{"title":"emrQA: A Large Corpus for Question Answering on Electronic Medical Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anusri Pampari, Jennifer Liang, Jian Peng, Preethi Raghavan","submitted_at":"2018-09-03T21:56:47Z","abstract_excerpt":"We propose a novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks. We demonstrate an instance of this methodology in generating a large-scale QA dataset for electronic medical records by leveraging existing expert annotations on clinical notes for various NLP tasks from the community shared i2b2 datasets. The resulting corpus (emrQA) has 1 million question-logical form and 400,000+ question-answer evidence pairs. We characterize the dataset and explore its learning potential by training baseline mode"},"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":"1809.00732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-03T21:56:47Z","cross_cats_sorted":[],"title_canon_sha256":"7480a5ac1e5aeae50e82bf773e938b5b763d4d7c2b38534a303c88c99df15ac5","abstract_canon_sha256":"b0839efd7833833a831a7eb8d6d94512d74b0da29c3e889fcd294a9127692869"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:32.629375Z","signature_b64":"WR3rr+0mYr9PQqHac+7qaNxSYhL+NfTnyq2izhSBBP8IvTDN+mWEBUwmt9eF7JcbNmEKUuDFyTL6kS2LoUWuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbc61809c6e0651d84842905a866020094080759853916233b772761f5cd211d","last_reissued_at":"2026-05-18T00:06:32.628892Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:32.628892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"emrQA: A Large Corpus for Question Answering on Electronic Medical Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anusri Pampari, Jennifer Liang, Jian Peng, Preethi Raghavan","submitted_at":"2018-09-03T21:56:47Z","abstract_excerpt":"We propose a novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks. We demonstrate an instance of this methodology in generating a large-scale QA dataset for electronic medical records by leveraging existing expert annotations on clinical notes for various NLP tasks from the community shared i2b2 datasets. The resulting corpus (emrQA) has 1 million question-logical form and 400,000+ question-answer evidence pairs. We characterize the dataset and explore its learning potential by training baseline mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00732","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":"1809.00732","created_at":"2026-05-18T00:06:32.628958+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.00732v1","created_at":"2026-05-18T00:06:32.628958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00732","created_at":"2026-05-18T00:06:32.628958+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PDBQCOG4BSR","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PDBQCOG4BSR3BEE","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PDBQCOG","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2305.09617","citing_title":"Towards Expert-Level Medical Question Answering with Large Language Models","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"1909.06146","citing_title":"PubMedQA: A Dataset for Biomedical Research Question Answering","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2502.18864","citing_title":"Towards an AI co-scientist","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":168,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC","json":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC.json","graph_json":"https://pith.science/api/pith-number/3PDBQCOG4BSR3BEEFEC2QZQCAC/graph.json","events_json":"https://pith.science/api/pith-number/3PDBQCOG4BSR3BEEFEC2QZQCAC/events.json","paper":"https://pith.science/paper/3PDBQCOG"},"agent_actions":{"view_html":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC","download_json":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC.json","view_paper":"https://pith.science/paper/3PDBQCOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.00732&json=true","fetch_graph":"https://pith.science/api/pith-number/3PDBQCOG4BSR3BEEFEC2QZQCAC/graph.json","fetch_events":"https://pith.science/api/pith-number/3PDBQCOG4BSR3BEEFEC2QZQCAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/action/storage_attestation","attest_author":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/action/author_attestation","sign_citation":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/action/citation_signature","submit_replication":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/action/replication_record"}},"created_at":"2026-05-18T00:06:32.628958+00:00","updated_at":"2026-05-18T00:06:32.628958+00:00"}