{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RXXUK3VJAUNZ6SASAT5GX2W26A","short_pith_number":"pith:RXXUK3VJ","schema_version":"1.0","canonical_sha256":"8def456ea9051b9f481204fa6beadaf006c7e9109881af56104da183202a17e2","source":{"kind":"arxiv","id":"2009.13081","version":1},"attestation_state":"computed","paper":{"title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Jin, Eileen Pan, Hanyi Fang, Nassim Oufattole, Peter Szolovits, Wei-Hung Weng","submitted_at":"2020-09-28T05:07:51Z","abstract_excerpt":"Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively. We implement both rule-based and popular neural methods by sequentially combining a document retriever and a m"},"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":"2009.13081","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-28T05:07:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4e822146c5d635f09f83d494e031285a14438544aed8dc645c3bef30e665ae61","abstract_canon_sha256":"830c1b3aea5640747f983b0d90ef4c5ff2d89710877be9303083a7df21cbcacd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:26.422047Z","signature_b64":"Dl6t7uBc2tq4A2BOFIpfEkaGjWa7Kr7u/88SJgQ1oc/mKZMedGftoQn/A0N7S5D6tFt2O/3r/0dzut4+mkj7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8def456ea9051b9f481204fa6beadaf006c7e9109881af56104da183202a17e2","last_reissued_at":"2026-07-05T01:38:26.421539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:26.421539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Jin, Eileen Pan, Hanyi Fang, Nassim Oufattole, Peter Szolovits, Wei-Hung Weng","submitted_at":"2020-09-28T05:07:51Z","abstract_excerpt":"Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively. We implement both rule-based and popular neural methods by sequentially combining a document retriever and a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13081","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.13081/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":"2009.13081","created_at":"2026-07-05T01:38:26.421600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13081v1","created_at":"2026-07-05T01:38:26.421600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13081","created_at":"2026-07-05T01:38:26.421600+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXXUK3VJAUNZ","created_at":"2026-07-05T01:38:26.421600+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXXUK3VJAUNZ6SAS","created_at":"2026-07-05T01:38:26.421600+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXXUK3VJ","created_at":"2026-07-05T01:38:26.421600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":39,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07761","citing_title":"Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21023","citing_title":"Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19396","citing_title":"BioHarness: Substrate-Aware Evidence Assembly for Biomedical Question Answering across Literature, Knowledge Bases, and Biological Atlases","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03305","citing_title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02007","citing_title":"EduArt: An educational-level benchmark for evaluating art history knowledge in large language models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10385","citing_title":"Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy Distillation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31432","citing_title":"Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07853","citing_title":"Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03305","citing_title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02245","citing_title":"When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31432","citing_title":"Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07096","citing_title":"Query-efficient model evaluation using cached responses","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15000","citing_title":"Quantifying and Mitigating Premature Closure in Frontier LLMs","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28332","citing_title":"When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29375","citing_title":"TriageRA-CCF: Source-Side Clinical Confidence and Coverage Signals for Adaptive Rank Budgeting in Medical LLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27860","citing_title":"C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00123","citing_title":"CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2405.02079","citing_title":"Argumentative Large Language Models for Explainable and Contestable Claim Verification","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16155","citing_title":"PRIMETIME : Limits of LLMs in Temporal Primitives","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16679","citing_title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19028","citing_title":"Learning When to Adapt","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18930","citing_title":"OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2508.12778","citing_title":"HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25346","citing_title":"SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08804","citing_title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A","json":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A.json","graph_json":"https://pith.science/api/pith-number/RXXUK3VJAUNZ6SASAT5GX2W26A/graph.json","events_json":"https://pith.science/api/pith-number/RXXUK3VJAUNZ6SASAT5GX2W26A/events.json","paper":"https://pith.science/paper/RXXUK3VJ"},"agent_actions":{"view_html":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A","download_json":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A.json","view_paper":"https://pith.science/paper/RXXUK3VJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13081&json=true","fetch_graph":"https://pith.science/api/pith-number/RXXUK3VJAUNZ6SASAT5GX2W26A/graph.json","fetch_events":"https://pith.science/api/pith-number/RXXUK3VJAUNZ6SASAT5GX2W26A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A/action/storage_attestation","attest_author":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A/action/author_attestation","sign_citation":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A/action/citation_signature","submit_replication":"https://pith.science/pith/RXXUK3VJAUNZ6SASAT5GX2W26A/action/replication_record"}},"created_at":"2026-07-05T01:38:26.421600+00:00","updated_at":"2026-07-05T01:38:26.421600+00:00"}