{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:76ZA335XRMNGHC2MXCBHRW7ENX","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":"b233a21109c71d5c9b8bf5a60dab8e570fcff35eb505329f26f5a408d580f7fe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T13:42:34Z","title_canon_sha256":"d0d27ff308afe6cfdfc68e4b136838f8709b5de56b5dd455419c20616de498a4"},"schema_version":"1.0","source":{"id":"2504.11186","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11186","created_at":"2026-07-05T10:49:30Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11186v1","created_at":"2026-07-05T10:49:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11186","created_at":"2026-07-05T10:49:30Z"},{"alias_kind":"pith_short_12","alias_value":"76ZA335XRMNG","created_at":"2026-07-05T10:49:30Z"},{"alias_kind":"pith_short_16","alias_value":"76ZA335XRMNGHC2M","created_at":"2026-07-05T10:49:30Z"},{"alias_kind":"pith_short_8","alias_value":"76ZA335X","created_at":"2026-07-05T10:49:30Z"}],"graph_snapshots":[{"event_id":"sha256:c2bd7ce6cd1772796a05debdcb2f09ea02aa2a2ef525ce070e57d3837618c104","target":"graph","created_at":"2026-07-05T10:49:30Z","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/2504.11186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in reasoning-focused large language models (LLMs) mark a shift from general LLMs toward models designed for complex decision-making, a crucial aspect in medicine. However, their performance in specialized domains like ophthalmology remains underexplored. This study comprehensively evaluated and compared the accuracy and reasoning capabilities of four newly developed reasoning-focused LLMs, namely DeepSeek-R1, OpenAI o1, o3-mini, and Gemini 2.0 Flash-Thinking. Each model was assessed using 5,888 multiple-choice ophthalmology exam questions from the MedMCQA dataset in zero-shot s","authors_text":"David Ziyou Chen, Dianbo Liu, Fares Antaki, Gabriel Dawei Yang, Hyunjae Kim, Kelvin Li, Ke Zou, Marcus Tan, Maxwell Singer, Minjie Zou, Qingyu Chen, Robert Chang, Sahana Srinivasan, Thaddaeus Wai Soon Lo, Xuguang Ai, Yih Chung Tham","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T13:42:34Z","title":"Benchmarking Next-Generation Reasoning-Focused Large Language Models in Ophthalmology: A Head-to-Head Evaluation on 5,888 Items"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11186","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":"sha256:50d2b3c206bf26ecc70caa2f185eb12743a21c67b308caf6ec3a3c4b1a85461d","target":"record","created_at":"2026-07-05T10:49:30Z","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":"b233a21109c71d5c9b8bf5a60dab8e570fcff35eb505329f26f5a408d580f7fe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T13:42:34Z","title_canon_sha256":"d0d27ff308afe6cfdfc68e4b136838f8709b5de56b5dd455419c20616de498a4"},"schema_version":"1.0","source":{"id":"2504.11186","kind":"arxiv","version":1}},"canonical_sha256":"ffb20defb78b1a638b4cb88278dbe46de32a685af89acf381ddf735150615397","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffb20defb78b1a638b4cb88278dbe46de32a685af89acf381ddf735150615397","first_computed_at":"2026-07-05T10:49:30.450949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:30.450949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V2F5k3E0geXo8JcsWyzeRB2gNUr+Ohcxk71/FjaF3OVD4QzBUnOcxjLhcV/RKaPGmDUgLSLljQczGDa1eaxGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:30.451477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11186","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50d2b3c206bf26ecc70caa2f185eb12743a21c67b308caf6ec3a3c4b1a85461d","sha256:c2bd7ce6cd1772796a05debdcb2f09ea02aa2a2ef525ce070e57d3837618c104"],"state_sha256":"49fa012036bc782456c40fef2302b8def2abd24096c151217f4ac3781320ad5b"}