{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3BS3J6M6H3HCFZ4NMWWGQR7ME3","short_pith_number":"pith:3BS3J6M6","schema_version":"1.0","canonical_sha256":"d865b4f99e3ece22e78d65ac6847ec26cd80fde4d5af0b29c9ead593734d09d1","source":{"kind":"arxiv","id":"2506.08349","version":1},"attestation_state":"computed","paper":{"title":"Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boxun Li, Chen Ning, Chenwei Yan, Guoping Hu, Ji Wu, Shijin Wang, Xiangling Fu, Xiao Zhang, Xien Liu, Yu Wang, Yuxuan Zhou","submitted_at":"2025-06-10T02:07:33Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance on various medical benchmarks, but their capabilities across different cognitive levels remain underexplored. Inspired by Bloom's Taxonomy, we propose a multi-cognitive-level evaluation framework for assessing LLMs in the medical domain in this study. The framework integrates existing medical datasets and introduces tasks targeting three cognitive levels: preliminary knowledge grasp, comprehensive knowledge application, and scenario-based problem solving. Using this framework, we systematically evaluate state-of-the-art gene"},"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":"2506.08349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T02:07:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25bc39b99e96f319042747ae6900dd84caefbd58a65ed6f7c63f76171285acab","abstract_canon_sha256":"0a61faa5b3049ac4af6bd391677b5dcc25248697f0611d7b99970f8b0c4825d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:48.384462Z","signature_b64":"PAyICEKAaQskA0LCQRiR7zBdXCXjKZ93h5/K/AUMxl2x1lYDIWrBjo3WvBXZ663k/ngEQbPIOkm2q/5x29CgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d865b4f99e3ece22e78d65ac6847ec26cd80fde4d5af0b29c9ead593734d09d1","last_reissued_at":"2026-07-05T11:18:48.384075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:48.384075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boxun Li, Chen Ning, Chenwei Yan, Guoping Hu, Ji Wu, Shijin Wang, Xiangling Fu, Xiao Zhang, Xien Liu, Yu Wang, Yuxuan Zhou","submitted_at":"2025-06-10T02:07:33Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance on various medical benchmarks, but their capabilities across different cognitive levels remain underexplored. Inspired by Bloom's Taxonomy, we propose a multi-cognitive-level evaluation framework for assessing LLMs in the medical domain in this study. The framework integrates existing medical datasets and introduces tasks targeting three cognitive levels: preliminary knowledge grasp, comprehensive knowledge application, and scenario-based problem solving. Using this framework, we systematically evaluate state-of-the-art gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08349","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/2506.08349/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":"2506.08349","created_at":"2026-07-05T11:18:48.384131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08349v1","created_at":"2026-07-05T11:18:48.384131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08349","created_at":"2026-07-05T11:18:48.384131+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BS3J6M6H3HC","created_at":"2026-07-05T11:18:48.384131+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BS3J6M6H3HCFZ4N","created_at":"2026-07-05T11:18:48.384131+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BS3J6M6","created_at":"2026-07-05T11:18:48.384131+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/3BS3J6M6H3HCFZ4NMWWGQR7ME3","json":"https://pith.science/pith/3BS3J6M6H3HCFZ4NMWWGQR7ME3.json","graph_json":"https://pith.science/api/pith-number/3BS3J6M6H3HCFZ4NMWWGQR7ME3/graph.json","events_json":"https://pith.science/api/pith-number/3BS3J6M6H3HCFZ4NMWWGQR7ME3/events.json","paper":"https://pith.science/paper/3BS3J6M6"},"agent_actions":{"view_html":"https://pith.science/pith/3BS3J6M6H3HCFZ4NMWWGQR7ME3","download_json":"https://pith.science/pith/3BS3J6M6H3HCFZ4NMWWGQR7ME3.json","view_paper":"https://pith.science/paper/3BS3J6M6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08349&json=true","fetch_graph":"https://pith.science/api/pith-number/3BS3J6M6H3HCFZ4NMWWGQR7ME3/graph.json","fetch_events":"https://pith.science/api/pith-number/3BS3J6M6H3HCFZ4NMWWGQR7ME3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BS3J6M6H3HCFZ4NMWWGQR7ME3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BS3J6M6H3HCFZ4NMWWGQR7ME3/action/storage_attestation","attest_author":"https://pith.science/pith/3BS3J6M6H3HCFZ4NMWWGQR7ME3/action/author_attestation","sign_citation":"https://pith.science/pith/3BS3J6M6H3HCFZ4NMWWGQR7ME3/action/citation_signature","submit_replication":"https://pith.science/pith/3BS3J6M6H3HCFZ4NMWWGQR7ME3/action/replication_record"}},"created_at":"2026-07-05T11:18:48.384131+00:00","updated_at":"2026-07-05T11:18:48.384131+00:00"}