{"id":"W4412877066","doi":"10.1145/3711896.3737435","title":"CURE: A dataset for Clinical Understanding & Retrieval Evaluation","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Montreal Clinical Research Institute","funders":"","keywords":"Computer science; Information retrieval; Artificial intelligence","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":[0.004433578,0.001865672,0.00147159,0.007577593,0.00104805,0.001947623,0.002506621,0.002759043,0.009752259],"category_scores_gemma":[0.02127776,0.0003608287,0.001655343,0.00457292,0.0007812008,0.00194764,0.002307844,0.001807193,0.0123114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0018354,"about_ca_system_score_gemma":0.002663004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01007906,"about_ca_topic_score_gemma":0.01773828,"domain_scores_codex":[0.9953507,0.001500214,0.000896412,0.0007769661,0.001213232,0.0002623913],"domain_scores_gemma":[0.9900013,0.004054431,0.0009257989,0.001979047,0.002195512,0.0008439083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001212325,0.001020536,0.01209619,0.005186322,0.000464531,0.0006761688,0.000529825,0.004040884,0.006106515,0.001983125,0.831825,0.1348586],"study_design_scores_gemma":[0.002650017,0.002407584,0.09097033,0.001525623,0.0007764244,0.005815408,0.001875149,0.04329035,0.01780334,0.006346771,0.8259997,0.0005393731],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.07194538,0.007199789,0.01837067,0.00326509,0.0007860741,0.003976871,0.8678876,0.009441182,0.0171273],"genre_scores_gemma":[0.03920935,0.0008007589,0.02030242,0.000587007,0.0001865235,0.001923299,0.933103,0.0003199147,0.003567658],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01007906,"threshold_uncertainty_score":0.03262448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4613842081861084,"score_gpt":0.4942159585426222,"score_spread":0.03283175035651376,"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."}}