{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7VNS5C3NNP575232QEGA3AMF4Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3d0d2391113d6509d253dd403cc9b2ffabf658e28ed7c5fab37774c19875fa87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T17:58:26Z","title_canon_sha256":"cb6ade6c8d26b807ea6db8ce2f97e2eabd39e16b45ed5664a69874556a6286ed"},"schema_version":"1.0","source":{"id":"2507.07988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07988","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07988v1","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07988","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"7VNS5C3NNP57","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_16","alias_value":"7VNS5C3NNP575232","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_8","alias_value":"7VNS5C3N","created_at":"2026-07-05T11:35:08Z"}],"graph_snapshots":[{"event_id":"sha256:43c80457725090edd0e3812e74284d3658dd2d95d24f411d009323b8574bf157","target":"graph","created_at":"2026-07-05T11:35:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.07988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T17:58:26Z","title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07988","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c1fe3a270bd9ede85ef6ade0df74400e13222a6dffa2b2ae80dc03aa8dfa2487","target":"record","created_at":"2026-07-05T11:35:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3d0d2391113d6509d253dd403cc9b2ffabf658e28ed7c5fab37774c19875fa87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T17:58:26Z","title_canon_sha256":"cb6ade6c8d26b807ea6db8ce2f97e2eabd39e16b45ed5664a69874556a6286ed"},"schema_version":"1.0","source":{"id":"2507.07988","kind":"arxiv","version":1}},"canonical_sha256":"fd5b2e8b6d6bfbfeeb7a810c0d8185e41505fc24aa91a6ab1f7d0f08d530fd47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd5b2e8b6d6bfbfeeb7a810c0d8185e41505fc24aa91a6ab1f7d0f08d530fd47","first_computed_at":"2026-07-05T11:35:08.016309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:08.016309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KbBgJg73rShr7ora3zcosqCzsQ17s7zvKjOJ47KxrCzfkgeGq/7P+eKkpz/2IQgwluaiytuoRHDlOLAry7foAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:08.017366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1fe3a270bd9ede85ef6ade0df74400e13222a6dffa2b2ae80dc03aa8dfa2487","sha256:43c80457725090edd0e3812e74284d3658dd2d95d24f411d009323b8574bf157"],"state_sha256":"020d027119d1f29b87883cb4717b70e464f8d96509c6688addedc03e2f217af4"}