{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7VNS5C3NNP575232QEGA3AMF4Q","short_pith_number":"pith:7VNS5C3N","schema_version":"1.0","canonical_sha256":"fd5b2e8b6d6bfbfeeb7a810c0d8185e41505fc24aa91a6ab1f7d0f08d530fd47","source":{"kind":"arxiv","id":"2507.07988","version":1},"attestation_state":"computed","paper":{"title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheyenna Espinoza, Emma Schaffer, Han Yang, Jiaxi Li, Lindsay Welton, Meijia Song, Meng-Han Tsai, Ninghao Liu, Rui Zhang, Shuang Zhou, Wenya Xie, Xinnie Mai, Yanwei Jin, Yiyun Xing, Yucheng Shi, Yuen-Hei Chung, Zaifu Zhan, Zidu Xu, Zirui Liu","submitted_at":"2025-07-10T17:58:26Z","abstract_excerpt":"As large language models (LLMs) become increasingly integrated into clinical decision-making, ensuring transparent and trustworthy reasoning is essential. However, existing evaluation strategies of LLMs' medical reasoning capability either suffer from unsatisfactory assessment or poor scalability, and a rigorous benchmark remains lacking. To address this, we introduce MedThink-Bench, a benchmark designed for rigorous, explainable, and scalable assessment of LLMs' medical reasoning. MedThink-Bench comprises 500 challenging questions across ten medical domains, each annotated with expert-crafted"},"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":"2507.07988","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T17:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"cb6ade6c8d26b807ea6db8ce2f97e2eabd39e16b45ed5664a69874556a6286ed","abstract_canon_sha256":"3d0d2391113d6509d253dd403cc9b2ffabf658e28ed7c5fab37774c19875fa87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:08.017366Z","signature_b64":"KbBgJg73rShr7ora3zcosqCzsQ17s7zvKjOJ47KxrCzfkgeGq/7P+eKkpz/2IQgwluaiytuoRHDlOLAry7foAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd5b2e8b6d6bfbfeeb7a810c0d8185e41505fc24aa91a6ab1f7d0f08d530fd47","last_reissued_at":"2026-07-05T11:35:08.016309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:08.016309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheyenna Espinoza, Emma Schaffer, Han Yang, Jiaxi Li, Lindsay Welton, Meijia Song, Meng-Han Tsai, Ninghao Liu, Rui Zhang, Shuang Zhou, Wenya Xie, Xinnie Mai, Yanwei Jin, Yiyun Xing, Yucheng Shi, Yuen-Hei Chung, Zaifu Zhan, Zidu Xu, Zirui Liu","submitted_at":"2025-07-10T17:58:26Z","abstract_excerpt":"As large language models (LLMs) become increasingly integrated into clinical decision-making, ensuring transparent and trustworthy reasoning is essential. However, existing evaluation strategies of LLMs' medical reasoning capability either suffer from unsatisfactory assessment or poor scalability, and a rigorous benchmark remains lacking. To address this, we introduce MedThink-Bench, a benchmark designed for rigorous, explainable, and scalable assessment of LLMs' medical reasoning. MedThink-Bench comprises 500 challenging questions across ten medical domains, each annotated with expert-crafted"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07988","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/2507.07988/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":"2507.07988","created_at":"2026-07-05T11:35:08.016501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07988v1","created_at":"2026-07-05T11:35:08.016501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07988","created_at":"2026-07-05T11:35:08.016501+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VNS5C3NNP57","created_at":"2026-07-05T11:35:08.016501+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VNS5C3NNP575232","created_at":"2026-07-05T11:35:08.016501+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VNS5C3N","created_at":"2026-07-05T11:35:08.016501+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/7VNS5C3NNP575232QEGA3AMF4Q","json":"https://pith.science/pith/7VNS5C3NNP575232QEGA3AMF4Q.json","graph_json":"https://pith.science/api/pith-number/7VNS5C3NNP575232QEGA3AMF4Q/graph.json","events_json":"https://pith.science/api/pith-number/7VNS5C3NNP575232QEGA3AMF4Q/events.json","paper":"https://pith.science/paper/7VNS5C3N"},"agent_actions":{"view_html":"https://pith.science/pith/7VNS5C3NNP575232QEGA3AMF4Q","download_json":"https://pith.science/pith/7VNS5C3NNP575232QEGA3AMF4Q.json","view_paper":"https://pith.science/paper/7VNS5C3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07988&json=true","fetch_graph":"https://pith.science/api/pith-number/7VNS5C3NNP575232QEGA3AMF4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/7VNS5C3NNP575232QEGA3AMF4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VNS5C3NNP575232QEGA3AMF4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VNS5C3NNP575232QEGA3AMF4Q/action/storage_attestation","attest_author":"https://pith.science/pith/7VNS5C3NNP575232QEGA3AMF4Q/action/author_attestation","sign_citation":"https://pith.science/pith/7VNS5C3NNP575232QEGA3AMF4Q/action/citation_signature","submit_replication":"https://pith.science/pith/7VNS5C3NNP575232QEGA3AMF4Q/action/replication_record"}},"created_at":"2026-07-05T11:35:08.016501+00:00","updated_at":"2026-07-05T11:35:08.016501+00:00"}