{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AVRVLSU7XNK7PR743PIABBV3N2","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":"7ccda2ef2f785474c5b5fb46d519bb753f49a648744b7bc6a6c564c794de47d6","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T15:25:38Z","title_canon_sha256":"ea8135fc9036394bd5ffa5b50ccfc11db59e874ebd763655331672a108354a2b"},"schema_version":"1.0","source":{"id":"2506.02987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02987","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02987v1","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02987","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"AVRVLSU7XNK7","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"AVRVLSU7XNK7PR74","created_at":"2026-07-05T11:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"AVRVLSU7","created_at":"2026-07-05T11:15:12Z"}],"graph_snapshots":[{"event_id":"sha256:b54828749b6ba22adfb2d81bde771e161f9be74b198040ed0debbc5530780337","target":"graph","created_at":"2026-07-05T11:15:12Z","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/2506.02987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background: Large language models (LLMs) have demonstrated substantial potential to support clinical practice. Other than Chat GPT4 and its predecessors, few LLMs, especially those of the leading and more powerful reasoning model class, have been subjected to medical specialty examination questions, including in the domain of primary care. This paper aimed to test the capabilities of leading LLMs as of May 2025 (o3, Claude Opus 4, Grok3, and Gemini 2.5 Pro) in primary care education, specifically in answering Member of the Royal College of General Practitioners (MRCGP) style examination questi","authors_text":"Richard Armitage","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T15:25:38Z","title":"Performance of leading large language models in May 2025 in Membership of the Royal College of General Practitioners-style examination questions: a cross-sectional analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02987","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:b6cd4df2ec4dd8437b7d76276618e6e8068eb4d12bf43d9e246557d8e6d24290","target":"record","created_at":"2026-07-05T11:15:12Z","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":"7ccda2ef2f785474c5b5fb46d519bb753f49a648744b7bc6a6c564c794de47d6","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T15:25:38Z","title_canon_sha256":"ea8135fc9036394bd5ffa5b50ccfc11db59e874ebd763655331672a108354a2b"},"schema_version":"1.0","source":{"id":"2506.02987","kind":"arxiv","version":1}},"canonical_sha256":"056355ca9fbb55f7c7fcdbd00086bb6e8fbac9597882af0635450b2cf4d2e380","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"056355ca9fbb55f7c7fcdbd00086bb6e8fbac9597882af0635450b2cf4d2e380","first_computed_at":"2026-07-05T11:15:12.969627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:12.969627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1PkO0sp8auod/NMAVxHAMH52z+p3RGZPFOwjg/J7YJOArtczQksWOi9hH99duyuVsPoX93CqaiGQ+b2ch0qNCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:12.970341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6cd4df2ec4dd8437b7d76276618e6e8068eb4d12bf43d9e246557d8e6d24290","sha256:b54828749b6ba22adfb2d81bde771e161f9be74b198040ed0debbc5530780337"],"state_sha256":"e8c15646dd90ca7e3651505d282a7b9be8d98d9954c27e73557378b4d20165f3"}