{"id":"W4411306282","doi":"10.1007/s41666-025-00204-w","title":"LongHealth: A Question Answering Benchmark with Long Clinical Documents","year":2025,"lang":"en","type":"article","venue":"Journal of Healthcare Informatics Research","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Technische Universität München","keywords":"Benchmark (surveying); Computer science; Sorting; Identification (biology); Unstructured data; Data science; Information retrieval; Data mining; Artificial intelligence; Natural language processing; Big data; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00692197,0.002106709,0.0008129067,0.00240427,0.0009345267,0.002290168,0.003580946,0.003464109,0.01011655],"category_scores_gemma":[0.0388884,0.0004804884,0.001249588,0.001989087,0.0009913255,0.002802691,0.002447468,0.002016258,0.005549141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002360492,"about_ca_system_score_gemma":0.002642635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01651224,"about_ca_topic_score_gemma":0.01810037,"domain_scores_codex":[0.9928361,0.003450789,0.0007891582,0.001491123,0.001151617,0.0002811942],"domain_scores_gemma":[0.9748908,0.01863298,0.0005593622,0.002060725,0.003026236,0.0008298088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004711462,0.002212934,0.02027028,0.006161406,0.0007657226,0.001873295,0.001581261,0.1138426,0.01185102,0.007789371,0.4111128,0.4178279],"study_design_scores_gemma":[0.0023236,0.002708957,0.02112528,0.001227799,0.0003365053,0.002491708,0.002317381,0.6862083,0.03897753,0.02803292,0.2138954,0.0003546734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4543073,0.02524376,0.137254,0.01717604,0.003336913,0.003177011,0.2049464,0.115119,0.0394395],"genre_scores_gemma":[0.5021556,0.001677558,0.1580939,0.003874267,0.0005334038,0.001248526,0.3214742,0.002347391,0.008595166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01651224,"threshold_uncertainty_score":0.03660733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1073749660151189,"score_gpt":0.5006962605306308,"score_spread":0.3933212945155119,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}