{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HIMRQZA2KF2GR3FEBBXP7MK3CF","short_pith_number":"pith:HIMRQZA2","schema_version":"1.0","canonical_sha256":"3a1918641a517468eca4086effb15b1151ca1fed7ad29aba2f33a38f637657b0","source":{"kind":"arxiv","id":"2506.00250","version":4},"attestation_state":"computed","paper":{"title":"PersianMedQA: Evaluating Large Language Models on a Persian-English Bilingual Medical Question Answering Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Amirhossein Sheikholselami, Azadeh Shakery, Heshaam Faili, Mohammad Javad Ranjbar Kalahroodi, Sepehr Karimi, Sepideh Ranjbar Kalahroodi","submitted_at":"2025-05-30T21:34:30Z","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"},"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":"2506.00250","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T21:34:30Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"e524a36c13a4a94fdc03bcacb43c0897549c7c3ef7d034efeabe43fd44cb8aa6","abstract_canon_sha256":"b38ca6ee72fffd9426a6f3118cd610fb4310328ddd46f179c4a6931f2ce3c58a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:34.905141Z","signature_b64":"EySSfFhx0I8wtTve1lMRyTiFxmvx/ixb/1NnSLW1A/34BlfE4a08HY+x0owhI1w7dXgbARuoe9T1BWdBZDgLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a1918641a517468eca4086effb15b1151ca1fed7ad29aba2f33a38f637657b0","last_reissued_at":"2026-05-27T01:05:34.904390Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:34.904390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PersianMedQA: Evaluating Large Language Models on a Persian-English Bilingual Medical Question Answering Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.CL","authors_text":"Amirhossein Sheikholselami, Azadeh Shakery, Heshaam Faili, Mohammad Javad Ranjbar Kalahroodi, Sepehr Karimi, Sepideh Ranjbar Kalahroodi","submitted_at":"2025-05-30T21:34:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00250","kind":"arxiv","version":4},"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/2506.00250/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":"2506.00250","created_at":"2026-05-27T01:05:34.904481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00250v4","created_at":"2026-05-27T01:05:34.904481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00250","created_at":"2026-05-27T01:05:34.904481+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIMRQZA2KF2G","created_at":"2026-05-27T01:05:34.904481+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIMRQZA2KF2GR3FE","created_at":"2026-05-27T01:05:34.904481+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIMRQZA2","created_at":"2026-05-27T01:05:34.904481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF","json":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF.json","graph_json":"https://pith.science/api/pith-number/HIMRQZA2KF2GR3FEBBXP7MK3CF/graph.json","events_json":"https://pith.science/api/pith-number/HIMRQZA2KF2GR3FEBBXP7MK3CF/events.json","paper":"https://pith.science/paper/HIMRQZA2"},"agent_actions":{"view_html":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF","download_json":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF.json","view_paper":"https://pith.science/paper/HIMRQZA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00250&json=true","fetch_graph":"https://pith.science/api/pith-number/HIMRQZA2KF2GR3FEBBXP7MK3CF/graph.json","fetch_events":"https://pith.science/api/pith-number/HIMRQZA2KF2GR3FEBBXP7MK3CF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF/action/storage_attestation","attest_author":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF/action/author_attestation","sign_citation":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF/action/citation_signature","submit_replication":"https://pith.science/pith/HIMRQZA2KF2GR3FEBBXP7MK3CF/action/replication_record"}},"created_at":"2026-05-27T01:05:34.904481+00:00","updated_at":"2026-05-27T01:05:34.904481+00:00"}