{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GXAQE4FTVUHQKRUZWCHLBFS3GV","short_pith_number":"pith:GXAQE4FT","schema_version":"1.0","canonical_sha256":"35c10270b3ad0f054699b08eb0965b357c6e966d1bb2afc294a2acc01aa62e35","source":{"kind":"arxiv","id":"2605.14543","version":1},"attestation_state":"computed","paper":{"title":"RxEval: A Prescription-Level Benchmark for Evaluating LLM Medication Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"RxEval tests LLMs on specific medication-dose-route choices from detailed patient trajectories, revealing top models reach only 46 percent exact match.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changmiao Wang, James T. Kwok, Shuhao Chen, Weisen Jiang, Xiaoqing Wu, Xuanren Shi, Yu Zhang","submitted_at":"2026-05-14T08:24:03Z","abstract_excerpt":"Inpatient medication recommendation requires clinicians to repeatedly select specific medications, doses, and routes as a patient's condition evolves. Existing benchmarks formulate this task as admission-level prediction over coarse drug codes with multi-hot diagnostic and procedure code inputs, failing to capture the per-timepoint, information-rich nature of real prescribing. We propose RxEval, a prescription-level benchmark that evaluates LLM prescribing capability by multiple-choice questions: each question presents a detailed patient profile and time-ordered clinical trajectory, requiring "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T08:24:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1af664d73bb3e41dd433329289b024f61317693e753b8f656274f4d4b30a9918","abstract_canon_sha256":"f790b35532a934599c0a9b7b83ba6e68f34ef850edfedf75c5903348287b9afa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:05.800878Z","signature_b64":"roHjDNhiBGPF54P5F4R2hdTiwo9QzTiIDNTsaa3ALGMWijCzGLfh7XN1kFdzGECOdYh05c3cWrC62ifzK0mzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35c10270b3ad0f054699b08eb0965b357c6e966d1bb2afc294a2acc01aa62e35","last_reissued_at":"2026-05-17T23:39:05.800113Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:05.800113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RxEval: A Prescription-Level Benchmark for Evaluating LLM Medication Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"RxEval tests LLMs on specific medication-dose-route choices from detailed patient trajectories, revealing top models reach only 46 percent exact match.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changmiao Wang, James T. Kwok, Shuhao Chen, Weisen Jiang, Xiaoqing Wu, Xuanren Shi, Yu Zhang","submitted_at":"2026-05-14T08:24:03Z","abstract_excerpt":"Inpatient medication recommendation requires clinicians to repeatedly select specific medications, doses, and routes as a patient's condition evolves. Existing benchmarks formulate this task as admission-level prediction over coarse drug codes with multi-hot diagnostic and procedure code inputs, failing to capture the per-timepoint, information-rich nature of real prescribing. We propose RxEval, a prescription-level benchmark that evaluates LLM prescribing capability by multiple-choice questions: each question presents a detailed patient profile and time-ordered clinical trajectory, requiring "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluation of 16 LLMs shows that RxEval is both challenging and discriminative: F1 ranges from 45.18 to 77.10 across models, and the best Exact Match is only 46.10%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The distractors generated by reasoning-chain perturbation are clinically valid and representative of the kinds of errors or alternatives that would actually arise in real prescribing decisions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RxEval benchmark shows frontier LLMs reach at most 46.10% exact match on prescription-level medication, dose, and route selection from real patient trajectories.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RxEval tests LLMs on specific medication-dose-route choices from detailed patient trajectories, revealing top models reach only 46 percent exact match.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"17d574d17628c75d8ef06a445f1d93a1bad856d7974a84f1acb947471e7a8d4d"},"source":{"id":"2605.14543","kind":"arxiv","version":1},"verdict":{"id":"29889642-0f2e-434a-8e13-0d5b65f6a1f4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:04:49.937450Z","strongest_claim":"Evaluation of 16 LLMs shows that RxEval is both challenging and discriminative: F1 ranges from 45.18 to 77.10 across models, and the best Exact Match is only 46.10%.","one_line_summary":"RxEval benchmark shows frontier LLMs reach at most 46.10% exact match on prescription-level medication, dose, and route selection from real patient trajectories.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The distractors generated by reasoning-chain perturbation are clinically valid and representative of the kinds of errors or alternatives that would actually arise in real prescribing decisions.","pith_extraction_headline":"RxEval tests LLMs on specific medication-dose-route choices from detailed patient trajectories, revealing top models reach only 46 percent exact match."},"references":{"count":54,"sample":[{"doi":"","year":null,"title":"V ALS MedQA leaderboard. Website. URLhttps://www.vals.ai/benchmarks/medqa","work_id":"61cbc542-3336-4a24-bd05-75d81dec0e07","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"K. Agyeman-Manu, T. A. Ghebreyesus, M. Maait, A. Rafila, L. Tom, N. T. Lima, and D. Wangmo. Prioritising the health and care workforce shortage: Protect, invest, together.The Lancet Global Health, 11 ","work_id":"a6d621d1-aff2-4deb-8f4d-a299611274e9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Z. Ali, Y . Huang, I. Ullah, J. Feng, C. Deng, N. Thierry, A. Khan, A. U. Jan, X. Shen, W. Rui, et al. Deep learning for medication recommendation: A systematic survey.Data Intelligence, 5(2):303–354,","work_id":"33b4fbfd-d5ca-4fa4-aaa8-b9af82c854f1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Qwen2.5 Technical Report","work_id":"d8432992-4980-4a81-85c7-9fa2c2b87f85","ref_index":4,"cited_arxiv_id":"2412.15115","is_internal_anchor":true},{"doi":"","year":2025,"title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","work_id":"5d613c2c-158f-488c-9981-fc9b82a5e093","ref_index":5,"cited_arxiv_id":"2505.08775","is_internal_anchor":true}],"resolved_work":54,"snapshot_sha256":"71532895065a8cf02743e66cce5d543ddf63822f924cab13e0f895b3f8f9b555","internal_anchors":12},"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":"2605.14543","created_at":"2026-05-17T23:39:05.800250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14543v1","created_at":"2026-05-17T23:39:05.800250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14543","created_at":"2026-05-17T23:39:05.800250+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXAQE4FTVUHQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXAQE4FTVUHQKRUZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXAQE4FT","created_at":"2026-05-18T12:33:37.589309+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/GXAQE4FTVUHQKRUZWCHLBFS3GV","json":"https://pith.science/pith/GXAQE4FTVUHQKRUZWCHLBFS3GV.json","graph_json":"https://pith.science/api/pith-number/GXAQE4FTVUHQKRUZWCHLBFS3GV/graph.json","events_json":"https://pith.science/api/pith-number/GXAQE4FTVUHQKRUZWCHLBFS3GV/events.json","paper":"https://pith.science/paper/GXAQE4FT"},"agent_actions":{"view_html":"https://pith.science/pith/GXAQE4FTVUHQKRUZWCHLBFS3GV","download_json":"https://pith.science/pith/GXAQE4FTVUHQKRUZWCHLBFS3GV.json","view_paper":"https://pith.science/paper/GXAQE4FT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14543&json=true","fetch_graph":"https://pith.science/api/pith-number/GXAQE4FTVUHQKRUZWCHLBFS3GV/graph.json","fetch_events":"https://pith.science/api/pith-number/GXAQE4FTVUHQKRUZWCHLBFS3GV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXAQE4FTVUHQKRUZWCHLBFS3GV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXAQE4FTVUHQKRUZWCHLBFS3GV/action/storage_attestation","attest_author":"https://pith.science/pith/GXAQE4FTVUHQKRUZWCHLBFS3GV/action/author_attestation","sign_citation":"https://pith.science/pith/GXAQE4FTVUHQKRUZWCHLBFS3GV/action/citation_signature","submit_replication":"https://pith.science/pith/GXAQE4FTVUHQKRUZWCHLBFS3GV/action/replication_record"}},"created_at":"2026-05-17T23:39:05.800250+00:00","updated_at":"2026-05-17T23:39:05.800250+00:00"}