{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6NU4J44LAZOFRNJKB5QVAWRZGE","short_pith_number":"pith:6NU4J44L","schema_version":"1.0","canonical_sha256":"f369c4f38b065c58b52a0f61505a393122d11a0f4a49c457baa37aad37d61a98","source":{"kind":"arxiv","id":"2502.17947","version":1},"attestation_state":"computed","paper":{"title":"DeepSeek-R1 Outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in Bilingual Complex Ophthalmology Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.CL","authors_text":"Danli Shi, Kai Jin, Mingguang He, Pusheng Xu, Xiaolan Chen, Yue Wu","submitted_at":"2025-02-25T08:08:53Z","abstract_excerpt":"Purpose: To evaluate the accuracy and reasoning ability of DeepSeek-R1 and three other recently released large language models (LLMs) in bilingual complex ophthalmology cases. Methods: A total of 130 multiple-choice questions (MCQs) related to diagnosis (n = 39) and management (n = 91) were collected from the Chinese ophthalmology senior professional title examination and categorized into six topics. These MCQs were translated into English using DeepSeek-R1. The responses of DeepSeek-R1, Gemini 2.0 Pro, OpenAI o1 and o3-mini were generated under default configurations between February 15 and F"},"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":"2502.17947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-25T08:08:53Z","cross_cats_sorted":["cs.AI","cs.PF"],"title_canon_sha256":"3349c5d56f886c3b40fd316bf7dbf7d22e136a5384926b95de4d43312b1e4193","abstract_canon_sha256":"e9e6ce645d70412fa7b0f0f244741347753fc2b42d2c15a4c20ef6c2cfe71843"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:46.662100Z","signature_b64":"N6cTHE10YNtQrlpjOty+PWnE2bvkSo881z3Y0GTyA3HLXMIrkaweFhfhzEWPFlOZblvUPasiGjQDMrJimVjiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f369c4f38b065c58b52a0f61505a393122d11a0f4a49c457baa37aad37d61a98","last_reissued_at":"2026-07-05T10:19:46.661646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:46.661646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepSeek-R1 Outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in Bilingual Complex Ophthalmology Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.PF"],"primary_cat":"cs.CL","authors_text":"Danli Shi, Kai Jin, Mingguang He, Pusheng Xu, Xiaolan Chen, Yue Wu","submitted_at":"2025-02-25T08:08:53Z","abstract_excerpt":"Purpose: To evaluate the accuracy and reasoning ability of DeepSeek-R1 and three other recently released large language models (LLMs) in bilingual complex ophthalmology cases. Methods: A total of 130 multiple-choice questions (MCQs) related to diagnosis (n = 39) and management (n = 91) were collected from the Chinese ophthalmology senior professional title examination and categorized into six topics. These MCQs were translated into English using DeepSeek-R1. The responses of DeepSeek-R1, Gemini 2.0 Pro, OpenAI o1 and o3-mini were generated under default configurations between February 15 and F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17947","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/2502.17947/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":"2502.17947","created_at":"2026-07-05T10:19:46.661705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17947v1","created_at":"2026-07-05T10:19:46.661705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17947","created_at":"2026-07-05T10:19:46.661705+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NU4J44LAZOF","created_at":"2026-07-05T10:19:46.661705+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NU4J44LAZOFRNJK","created_at":"2026-07-05T10:19:46.661705+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NU4J44L","created_at":"2026-07-05T10:19:46.661705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01257","citing_title":"DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE","json":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE.json","graph_json":"https://pith.science/api/pith-number/6NU4J44LAZOFRNJKB5QVAWRZGE/graph.json","events_json":"https://pith.science/api/pith-number/6NU4J44LAZOFRNJKB5QVAWRZGE/events.json","paper":"https://pith.science/paper/6NU4J44L"},"agent_actions":{"view_html":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE","download_json":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE.json","view_paper":"https://pith.science/paper/6NU4J44L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17947&json=true","fetch_graph":"https://pith.science/api/pith-number/6NU4J44LAZOFRNJKB5QVAWRZGE/graph.json","fetch_events":"https://pith.science/api/pith-number/6NU4J44LAZOFRNJKB5QVAWRZGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE/action/storage_attestation","attest_author":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE/action/author_attestation","sign_citation":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE/action/citation_signature","submit_replication":"https://pith.science/pith/6NU4J44LAZOFRNJKB5QVAWRZGE/action/replication_record"}},"created_at":"2026-07-05T10:19:46.661705+00:00","updated_at":"2026-07-05T10:19:46.661705+00:00"}