{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AR4KE2RRORVHJBNMBYREXODSTP","short_pith_number":"pith:AR4KE2RR","schema_version":"1.0","canonical_sha256":"0478a26a31746a7485ac0e224bb8729bd78448f40dd44ce6adf1fe07df582821","source":{"kind":"arxiv","id":"2502.01243","version":1},"attestation_state":"computed","paper":{"title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengfeng Zhou, Ji Wang, Juanjuan Qin, Ling Sun, Weiwei Dai, Yining Wang","submitted_at":"2025-02-03T11:04:51Z","abstract_excerpt":"Large language models (LLMs) have shown significant promise across various medical applications, with ophthalmology being a notable area of focus. Many ophthalmic tasks have shown substantial improvement through the integration of LLMs. However, before these models can be widely adopted in clinical practice, evaluating their capabilities and identifying their limitations is crucial. To address this research gap and support the real-world application of LLMs, we introduce the OphthBench, a specialized benchmark designed to assess LLM performance within the context of Chinese ophthalmic practice"},"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":"2502.01243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T11:04:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b834409385b005b1d47a8d9168eb05423300db49e64afb4f2312ee19072cf7df","abstract_canon_sha256":"2c092e8b855cb67413c5a4101719eb654c7ce44f6f7d15cffadbd6c94b873065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:44.727062Z","signature_b64":"yHHLKWp6t1QdujfmPfrG88ndvIFf+payHNelxMDK00Oy8ZIJHOJGW9/7y9WSGky8VXFEfDgDIXaOk+ghXBkQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0478a26a31746a7485ac0e224bb8729bd78448f40dd44ce6adf1fe07df582821","last_reissued_at":"2026-07-05T10:08:44.726539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:44.726539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengfeng Zhou, Ji Wang, Juanjuan Qin, Ling Sun, Weiwei Dai, Yining Wang","submitted_at":"2025-02-03T11:04:51Z","abstract_excerpt":"Large language models (LLMs) have shown significant promise across various medical applications, with ophthalmology being a notable area of focus. Many ophthalmic tasks have shown substantial improvement through the integration of LLMs. However, before these models can be widely adopted in clinical practice, evaluating their capabilities and identifying their limitations is crucial. To address this research gap and support the real-world application of LLMs, we introduce the OphthBench, a specialized benchmark designed to assess LLM performance within the context of Chinese ophthalmic practice"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01243","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/2502.01243/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":"2502.01243","created_at":"2026-07-05T10:08:44.726598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01243v1","created_at":"2026-07-05T10:08:44.726598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01243","created_at":"2026-07-05T10:08:44.726598+00:00"},{"alias_kind":"pith_short_12","alias_value":"AR4KE2RRORVH","created_at":"2026-07-05T10:08:44.726598+00:00"},{"alias_kind":"pith_short_16","alias_value":"AR4KE2RRORVHJBNM","created_at":"2026-07-05T10:08:44.726598+00:00"},{"alias_kind":"pith_short_8","alias_value":"AR4KE2RR","created_at":"2026-07-05T10:08:44.726598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15717","citing_title":"BEnchmarking LLMs for Ophthalmology (BELO) for Ophthalmological Knowledge and Reasoning","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP","json":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP.json","graph_json":"https://pith.science/api/pith-number/AR4KE2RRORVHJBNMBYREXODSTP/graph.json","events_json":"https://pith.science/api/pith-number/AR4KE2RRORVHJBNMBYREXODSTP/events.json","paper":"https://pith.science/paper/AR4KE2RR"},"agent_actions":{"view_html":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP","download_json":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP.json","view_paper":"https://pith.science/paper/AR4KE2RR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01243&json=true","fetch_graph":"https://pith.science/api/pith-number/AR4KE2RRORVHJBNMBYREXODSTP/graph.json","fetch_events":"https://pith.science/api/pith-number/AR4KE2RRORVHJBNMBYREXODSTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP/action/storage_attestation","attest_author":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP/action/author_attestation","sign_citation":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP/action/citation_signature","submit_replication":"https://pith.science/pith/AR4KE2RRORVHJBNMBYREXODSTP/action/replication_record"}},"created_at":"2026-07-05T10:08:44.726598+00:00","updated_at":"2026-07-05T10:08:44.726598+00:00"}