{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XLP6RMQVPDLZETD5N2V6WF6LTI","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":"c18bbab8b09bf9e03b35375b375992b0ff5cc6f26f84fc983427659e32e42484","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-22T01:02:44Z","title_canon_sha256":"ec26f3224cfb9b5eeec00d49dc8416587d2cec2194f33e3f0dd8b57fa01e57cd"},"schema_version":"1.0","source":{"id":"2503.17599","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17599","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17599v3","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17599","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"XLP6RMQVPDLZ","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"XLP6RMQVPDLZETD5","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"XLP6RMQV","created_at":"2026-05-22T01:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:56124aa87681e68061453cc887189c34a52ca7507b6335b0fc5980702a27e054","target":"graph","created_at":"2026-05-22T01:03:42Z","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/2503.17599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated considerable potential in general practice. However, existing benchmarks and evaluation frameworks primarily depend on exam-style or simplified question-answer formats, lacking a competency-based structure aligned with the real-world clinical responsibilities encountered in general practice. Consequently, the extent to which LLMs can reliably fulfill the duties of general practitioners (GPs) remains uncertain. In this work, we propose a novel evaluation framework to assess the capability of LLMs to function as GPs. Based on this framework, we intr","authors_text":"Dingqian Wang, Hongji Yu, Jiexian Qiu, Jiping Lang, Junrong Chen, Lin Yao, Shuang Chen, Shuang Li, Wenhao Jiang, Xiaofei Zeng, Xiaolin Lu, Xuanna Li, Yixian Chen, Yiying Yang, Yuhang Zhao, Yuhua Bi, Yuze Tang, Zheqing Li, Zhu Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-22T01:02:44Z","title":"Evaluating Clinical Competencies of Large Language Models with a General Practice Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17599","kind":"arxiv","version":3},"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:da2db556be4c28b57d89585b8719ba813b3242681017f4294f5e5076dc37abd6","target":"record","created_at":"2026-05-22T01:03:42Z","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":"c18bbab8b09bf9e03b35375b375992b0ff5cc6f26f84fc983427659e32e42484","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-22T01:02:44Z","title_canon_sha256":"ec26f3224cfb9b5eeec00d49dc8416587d2cec2194f33e3f0dd8b57fa01e57cd"},"schema_version":"1.0","source":{"id":"2503.17599","kind":"arxiv","version":3}},"canonical_sha256":"badfe8b21578d7924c7d6eabeb17cb9a148117adb439ab586a34511579849dab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"badfe8b21578d7924c7d6eabeb17cb9a148117adb439ab586a34511579849dab","first_computed_at":"2026-05-22T01:03:42.237877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:42.237877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jxr3ZgU5bHhafz29TlFP/005R5PEQ4+Y9FAFLbxsmlc/zhY1+4AYx66CnwffLKsGDa6Ygqw/cqDDCyAgjQjwBA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:42.238784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17599","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da2db556be4c28b57d89585b8719ba813b3242681017f4294f5e5076dc37abd6","sha256:56124aa87681e68061453cc887189c34a52ca7507b6335b0fc5980702a27e054"],"state_sha256":"be5f5bbae52c261a31e5a6aa77588c8cdd315876606f01777f2f4fa711b5f801"}