{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CCAPLEAOYNSJ7KQRVR6VCZ6AJH","short_pith_number":"pith:CCAPLEAO","schema_version":"1.0","canonical_sha256":"1080f5900ec3649faa11ac7d5167c049f94b761828875ffd02aabf8ec6958aaa","source":{"kind":"arxiv","id":"2509.07135","version":1},"attestation_state":"computed","paper":{"title":"MedBench-IT: A Comprehensive Benchmark for Evaluating Large Language Models on Italian Medical Entrance Examinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessandro Angioi, Davide Sanna, Michelangelo Puliga, Roberto Marras, Ruggero Marino Lazzaroni","submitted_at":"2025-09-08T18:39:35Z","abstract_excerpt":"Large language models (LLMs) show increasing potential in education, yet benchmarks for non-English languages in specialized domains remain scarce. We introduce MedBench-IT, the first comprehensive benchmark for evaluating LLMs on Italian medical university entrance examinations. Sourced from Edizioni Simone, a leading preparatory materials publisher, MedBench-IT comprises 17,410 expert-written multiple-choice questions across six subjects (Biology, Chemistry, Logic, General Culture, Mathematics, Physics) and three difficulty levels. We evaluated diverse models including proprietary LLMs (GPT-"},"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":"2509.07135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T18:39:35Z","cross_cats_sorted":[],"title_canon_sha256":"db0abb7e10d7a9e6e277b22f0f208b71e8895d891280304cc78235675f33e297","abstract_canon_sha256":"1ba31cd11022a75d96f4c6de560718852bab84f5d195bed1a4d34a0332aded85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:16.147429Z","signature_b64":"PD14APgaEamnRuSkGpPBcaednC9m4vILF1eX8uvvt7hUmEnNcSOgM3ohRPAYnZGppa6t341o7vo4TzSbGrhSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1080f5900ec3649faa11ac7d5167c049f94b761828875ffd02aabf8ec6958aaa","last_reissued_at":"2026-07-05T12:07:16.146914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:16.146914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedBench-IT: A Comprehensive Benchmark for Evaluating Large Language Models on Italian Medical Entrance Examinations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessandro Angioi, Davide Sanna, Michelangelo Puliga, Roberto Marras, Ruggero Marino Lazzaroni","submitted_at":"2025-09-08T18:39:35Z","abstract_excerpt":"Large language models (LLMs) show increasing potential in education, yet benchmarks for non-English languages in specialized domains remain scarce. We introduce MedBench-IT, the first comprehensive benchmark for evaluating LLMs on Italian medical university entrance examinations. Sourced from Edizioni Simone, a leading preparatory materials publisher, MedBench-IT comprises 17,410 expert-written multiple-choice questions across six subjects (Biology, Chemistry, Logic, General Culture, Mathematics, Physics) and three difficulty levels. We evaluated diverse models including proprietary LLMs (GPT-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07135","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/2509.07135/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":"2509.07135","created_at":"2026-07-05T12:07:16.146972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07135v1","created_at":"2026-07-05T12:07:16.146972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07135","created_at":"2026-07-05T12:07:16.146972+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCAPLEAOYNSJ","created_at":"2026-07-05T12:07:16.146972+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCAPLEAOYNSJ7KQR","created_at":"2026-07-05T12:07:16.146972+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCAPLEAO","created_at":"2026-07-05T12:07:16.146972+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/CCAPLEAOYNSJ7KQRVR6VCZ6AJH","json":"https://pith.science/pith/CCAPLEAOYNSJ7KQRVR6VCZ6AJH.json","graph_json":"https://pith.science/api/pith-number/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/graph.json","events_json":"https://pith.science/api/pith-number/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/events.json","paper":"https://pith.science/paper/CCAPLEAO"},"agent_actions":{"view_html":"https://pith.science/pith/CCAPLEAOYNSJ7KQRVR6VCZ6AJH","download_json":"https://pith.science/pith/CCAPLEAOYNSJ7KQRVR6VCZ6AJH.json","view_paper":"https://pith.science/paper/CCAPLEAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07135&json=true","fetch_graph":"https://pith.science/api/pith-number/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/graph.json","fetch_events":"https://pith.science/api/pith-number/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/action/storage_attestation","attest_author":"https://pith.science/pith/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/action/author_attestation","sign_citation":"https://pith.science/pith/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/action/citation_signature","submit_replication":"https://pith.science/pith/CCAPLEAOYNSJ7KQRVR6VCZ6AJH/action/replication_record"}},"created_at":"2026-07-05T12:07:16.146972+00:00","updated_at":"2026-07-05T12:07:16.146972+00:00"}