{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZOZWOFVCBZHFPVFGTWQFQQKEPO","short_pith_number":"pith:ZOZWOFVC","schema_version":"1.0","canonical_sha256":"cbb36716a20e4e57d4a69da05841447b967ccba092751858134a1a5e73f09272","source":{"kind":"arxiv","id":"2310.07225","version":3},"attestation_state":"computed","paper":{"title":"Do Large Language Models have Shared Weaknesses in Medical Question Answering?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Mahdi, Andrew M. Bean, Felix Krones, Karolina Korgul, Robert McCraith","submitted_at":"2023-10-11T06:26:19Z","abstract_excerpt":"Large language models (LLMs) have made rapid improvement on medical benchmarks, but their unreliability remains a persistent challenge for safe real-world uses. To design for the use LLMs as a category, rather than for specific models, requires developing an understanding of shared strengths and weaknesses which appear across models. To address this challenge, we benchmark a range of top LLMs and identify consistent patterns across models. We test $16$ well-known LLMs on $874$ newly collected questions from Polish medical licensing exams. For each question, we score each model on the top-1 acc"},"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":"2310.07225","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T06:26:19Z","cross_cats_sorted":[],"title_canon_sha256":"fe126da26e62d7bbc3474562acec2fd7c78da8201db1ae8aff2dc86c64a65ccc","abstract_canon_sha256":"4697ac501c0da4b401d5d907fb32babd11c0c57848c8ed5aa80790da67c36be5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:06.635837Z","signature_b64":"veZa1p1tfoaORHpz6E3hzBSqAP3TkaRjxjm2itJ+0pNAUYY1EGX1fpw3oosiagQEbTqm2EkDbgLKSOiLS3YYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbb36716a20e4e57d4a69da05841447b967ccba092751858134a1a5e73f09272","last_reissued_at":"2026-07-05T09:19:06.635355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:06.635355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Large Language Models have Shared Weaknesses in Medical Question Answering?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Mahdi, Andrew M. Bean, Felix Krones, Karolina Korgul, Robert McCraith","submitted_at":"2023-10-11T06:26:19Z","abstract_excerpt":"Large language models (LLMs) have made rapid improvement on medical benchmarks, but their unreliability remains a persistent challenge for safe real-world uses. To design for the use LLMs as a category, rather than for specific models, requires developing an understanding of shared strengths and weaknesses which appear across models. To address this challenge, we benchmark a range of top LLMs and identify consistent patterns across models. We test $16$ well-known LLMs on $874$ newly collected questions from Polish medical licensing exams. For each question, we score each model on the top-1 acc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07225","kind":"arxiv","version":3},"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/2310.07225/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":"2310.07225","created_at":"2026-07-05T09:19:06.635416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07225v3","created_at":"2026-07-05T09:19:06.635416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07225","created_at":"2026-07-05T09:19:06.635416+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOZWOFVCBZHF","created_at":"2026-07-05T09:19:06.635416+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOZWOFVCBZHFPVFG","created_at":"2026-07-05T09:19:06.635416+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOZWOFVC","created_at":"2026-07-05T09:19:06.635416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO","json":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO.json","graph_json":"https://pith.science/api/pith-number/ZOZWOFVCBZHFPVFGTWQFQQKEPO/graph.json","events_json":"https://pith.science/api/pith-number/ZOZWOFVCBZHFPVFGTWQFQQKEPO/events.json","paper":"https://pith.science/paper/ZOZWOFVC"},"agent_actions":{"view_html":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO","download_json":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO.json","view_paper":"https://pith.science/paper/ZOZWOFVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07225&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOZWOFVCBZHFPVFGTWQFQQKEPO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOZWOFVCBZHFPVFGTWQFQQKEPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO/action/storage_attestation","attest_author":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO/action/author_attestation","sign_citation":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO/action/citation_signature","submit_replication":"https://pith.science/pith/ZOZWOFVCBZHFPVFGTWQFQQKEPO/action/replication_record"}},"created_at":"2026-07-05T09:19:06.635416+00:00","updated_at":"2026-07-05T09:19:06.635416+00:00"}