{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7GCHZUZOAEUW2S4DS2PC3BJWTC","short_pith_number":"pith:7GCHZUZO","schema_version":"1.0","canonical_sha256":"f9847cd32e01296d4b83969e2d8536989ba1b751d28b699e70d0144729a0a31b","source":{"kind":"arxiv","id":"2203.14371","version":1},"attestation_state":"computed","paper":{"title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankit Pal, Logesh Kumar Umapathi, Malaikannan Sankarasubbu","submitted_at":"2022-03-27T18:59:16Z","abstract_excerpt":"This paper introduces MedMCQA, a new large-scale, Multiple-Choice Question Answering (MCQA) dataset designed to address real-world medical entrance exam questions. More than 194k high-quality AIIMS \\& NEET PG entrance exam MCQs covering 2.4k healthcare topics and 21 medical subjects are collected with an average token length of 12.77 and high topical diversity. Each sample contains a question, correct answer(s), and other options which requires a deeper language understanding as it tests the 10+ reasoning abilities of a model across a wide range of medical subjects \\& topics. A detailed explan"},"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":"2203.14371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-27T18:59:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1e3985584c2338e79d3da80427de67c06923984a9f360124815e6bd4b8975010","abstract_canon_sha256":"345fa5ea088328f6c6c05837106bd09a3e4c12e983ea239eb3cc9f9d52792bcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:04.150355Z","signature_b64":"9IlAjVqCN2aC7yfFYw3U0MrgzUy+W8R0v7qeJiz4blwFEdsdmQyz9RP8X/h3t+aEBoZRnqqg64T+VkzVR3QsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9847cd32e01296d4b83969e2d8536989ba1b751d28b699e70d0144729a0a31b","last_reissued_at":"2026-07-05T04:09:04.149958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:04.149958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankit Pal, Logesh Kumar Umapathi, Malaikannan Sankarasubbu","submitted_at":"2022-03-27T18:59:16Z","abstract_excerpt":"This paper introduces MedMCQA, a new large-scale, Multiple-Choice Question Answering (MCQA) dataset designed to address real-world medical entrance exam questions. More than 194k high-quality AIIMS \\& NEET PG entrance exam MCQs covering 2.4k healthcare topics and 21 medical subjects are collected with an average token length of 12.77 and high topical diversity. Each sample contains a question, correct answer(s), and other options which requires a deeper language understanding as it tests the 10+ reasoning abilities of a model across a wide range of medical subjects \\& topics. A detailed explan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14371","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/2203.14371/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":"2203.14371","created_at":"2026-07-05T04:09:04.150016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14371v1","created_at":"2026-07-05T04:09:04.150016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14371","created_at":"2026-07-05T04:09:04.150016+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GCHZUZOAEUW","created_at":"2026-07-05T04:09:04.150016+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GCHZUZOAEUW2S4D","created_at":"2026-07-05T04:09:04.150016+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GCHZUZO","created_at":"2026-07-05T04:09:04.150016+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19266","citing_title":"Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA","ref_index":3,"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":25,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01103","citing_title":"Clinician-Level Agreement Without Clinical Caution: LLM Evaluator Limits in Medical AI Benchmarking","ref_index":8,"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":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24699","citing_title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30529","citing_title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21949","citing_title":"Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22047","citing_title":"Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision Support","ref_index":6,"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":44,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20983","citing_title":"Automatic Replication of LLM Mistakes in Medical Conversations","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":220,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09315","citing_title":"Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11547","citing_title":"Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10718","citing_title":"SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC","json":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC.json","graph_json":"https://pith.science/api/pith-number/7GCHZUZOAEUW2S4DS2PC3BJWTC/graph.json","events_json":"https://pith.science/api/pith-number/7GCHZUZOAEUW2S4DS2PC3BJWTC/events.json","paper":"https://pith.science/paper/7GCHZUZO"},"agent_actions":{"view_html":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC","download_json":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC.json","view_paper":"https://pith.science/paper/7GCHZUZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14371&json=true","fetch_graph":"https://pith.science/api/pith-number/7GCHZUZOAEUW2S4DS2PC3BJWTC/graph.json","fetch_events":"https://pith.science/api/pith-number/7GCHZUZOAEUW2S4DS2PC3BJWTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC/action/storage_attestation","attest_author":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC/action/author_attestation","sign_citation":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC/action/citation_signature","submit_replication":"https://pith.science/pith/7GCHZUZOAEUW2S4DS2PC3BJWTC/action/replication_record"}},"created_at":"2026-07-05T04:09:04.150016+00:00","updated_at":"2026-07-05T04:09:04.150016+00:00"}