{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GGPIPIH4YHOUOF5QUXUAPUDT43","short_pith_number":"pith:GGPIPIH4","schema_version":"1.0","canonical_sha256":"319e87a0fcc1dd4717b0a5e807d073e6d6e92d903c2202456ae65106a9ed233e","source":{"kind":"arxiv","id":"2406.02919","version":1},"attestation_state":"computed","paper":{"title":"MultifacetEval: Multifaceted Evaluation to Probe LLMs in Mastering Medical Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Ning, Ji Wu, Xien Liu, Yuxuan Zhou","submitted_at":"2024-06-05T04:15:07Z","abstract_excerpt":"Large language models (LLMs) have excelled across domains, also delivering notable performance on the medical evaluation benchmarks, such as MedQA. However, there still exists a significant gap between the reported performance and the practical effectiveness in real-world medical scenarios. In this paper, we aim to explore the causes of this gap by employing a multifaceted examination schema to systematically probe the actual mastery of medical knowledge by current LLMs. Specifically, we develop a novel evaluation framework MultifacetEval to examine the degree and coverage of LLMs in encoding "},"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":"2406.02919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T04:15:07Z","cross_cats_sorted":[],"title_canon_sha256":"892df28e4234b5483a88b956e228e100c10c5c1079dfaed7c821ddd0d8a16dcf","abstract_canon_sha256":"0b4416d89f5a31feeb88d1a99df40aa9807d9dc7756b2ded1187fcb1e3d44031"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:32.687609Z","signature_b64":"o/AllqPJ1T5zY7FOg+xIlpbkQOFihXLODgmW5VnS1++Z5exQymwCH+U9dE/22crDGC+49n7QyFIUQHBv/nlDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"319e87a0fcc1dd4717b0a5e807d073e6d6e92d903c2202456ae65106a9ed233e","last_reissued_at":"2026-07-05T08:27:32.687132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:32.687132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultifacetEval: Multifaceted Evaluation to Probe LLMs in Mastering Medical Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Ning, Ji Wu, Xien Liu, Yuxuan Zhou","submitted_at":"2024-06-05T04:15:07Z","abstract_excerpt":"Large language models (LLMs) have excelled across domains, also delivering notable performance on the medical evaluation benchmarks, such as MedQA. However, there still exists a significant gap between the reported performance and the practical effectiveness in real-world medical scenarios. In this paper, we aim to explore the causes of this gap by employing a multifaceted examination schema to systematically probe the actual mastery of medical knowledge by current LLMs. Specifically, we develop a novel evaluation framework MultifacetEval to examine the degree and coverage of LLMs in encoding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02919","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/2406.02919/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":"2406.02919","created_at":"2026-07-05T08:27:32.687196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02919v1","created_at":"2026-07-05T08:27:32.687196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02919","created_at":"2026-07-05T08:27:32.687196+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGPIPIH4YHOU","created_at":"2026-07-05T08:27:32.687196+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGPIPIH4YHOUOF5Q","created_at":"2026-07-05T08:27:32.687196+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGPIPIH4","created_at":"2026-07-05T08:27:32.687196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30637","citing_title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22258","citing_title":"Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43","json":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43.json","graph_json":"https://pith.science/api/pith-number/GGPIPIH4YHOUOF5QUXUAPUDT43/graph.json","events_json":"https://pith.science/api/pith-number/GGPIPIH4YHOUOF5QUXUAPUDT43/events.json","paper":"https://pith.science/paper/GGPIPIH4"},"agent_actions":{"view_html":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43","download_json":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43.json","view_paper":"https://pith.science/paper/GGPIPIH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02919&json=true","fetch_graph":"https://pith.science/api/pith-number/GGPIPIH4YHOUOF5QUXUAPUDT43/graph.json","fetch_events":"https://pith.science/api/pith-number/GGPIPIH4YHOUOF5QUXUAPUDT43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43/action/storage_attestation","attest_author":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43/action/author_attestation","sign_citation":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43/action/citation_signature","submit_replication":"https://pith.science/pith/GGPIPIH4YHOUOF5QUXUAPUDT43/action/replication_record"}},"created_at":"2026-07-05T08:27:32.687196+00:00","updated_at":"2026-07-05T08:27:32.687196+00:00"}