{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HIMRQZA2KF2GR3FEBBXP7MK3CF","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":"b38ca6ee72fffd9426a6f3118cd610fb4310328ddd46f179c4a6931f2ce3c58a","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:34:30Z","title_canon_sha256":"e524a36c13a4a94fdc03bcacb43c0897549c7c3ef7d034efeabe43fd44cb8aa6"},"schema_version":"1.0","source":{"id":"2506.00250","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00250","created_at":"2026-05-27T01:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00250v4","created_at":"2026-05-27T01:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00250","created_at":"2026-05-27T01:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"HIMRQZA2KF2G","created_at":"2026-05-27T01:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"HIMRQZA2KF2GR3FE","created_at":"2026-05-27T01:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"HIMRQZA2","created_at":"2026-05-27T01:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:daf46c53bf3544461bd96fbd11e03bad444723aae820b33d97db18c1786d9b27","target":"graph","created_at":"2026-05-27T01:05:34Z","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/2506.00250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable performance on a wide range of Natural Language Processing (NLP) benchmarks, often surpassing human-level accuracy. However, their reliability in high-stakes domains such as medicine, particularly in low-resource languages, remains underexplored. In this work, we introduce PersianMedQA, a large-scale dataset of 20,785 expert-validated multiple-choice Persian medical questions from 14 years of Iranian national medical exams, spanning 23 medical specialties and designed to evaluate LLMs in both Persian and English. We benchmark 41 state-of-th","authors_text":"Amirhossein Sheikholselami, Azadeh Shakery, Heshaam Faili, Mohammad Javad Ranjbar Kalahroodi, Sepehr Karimi, Sepideh Ranjbar Kalahroodi","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:34:30Z","title":"PersianMedQA: Evaluating Large Language Models on a Persian-English Bilingual Medical Question Answering Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00250","kind":"arxiv","version":4},"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":"sha256:09e1a6b89fb2814a753b1625b421e5e8279035b65ece315ba0d69571d2d7fecd","target":"record","created_at":"2026-05-27T01:05:34Z","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":"b38ca6ee72fffd9426a6f3118cd610fb4310328ddd46f179c4a6931f2ce3c58a","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:34:30Z","title_canon_sha256":"e524a36c13a4a94fdc03bcacb43c0897549c7c3ef7d034efeabe43fd44cb8aa6"},"schema_version":"1.0","source":{"id":"2506.00250","kind":"arxiv","version":4}},"canonical_sha256":"3a1918641a517468eca4086effb15b1151ca1fed7ad29aba2f33a38f637657b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a1918641a517468eca4086effb15b1151ca1fed7ad29aba2f33a38f637657b0","first_computed_at":"2026-05-27T01:05:34.904390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:34.904390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EySSfFhx0I8wtTve1lMRyTiFxmvx/ixb/1NnSLW1A/34BlfE4a08HY+x0owhI1w7dXgbARuoe9T1BWdBZDgLAQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:34.905141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00250","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09e1a6b89fb2814a753b1625b421e5e8279035b65ece315ba0d69571d2d7fecd","sha256:daf46c53bf3544461bd96fbd11e03bad444723aae820b33d97db18c1786d9b27"],"state_sha256":"3a1d326676943e342d9b3a93499555ddd343493b20dc9da31a745b6b17403ea8"}