{"id":"W2280717170","doi":"10.1007/978-3-319-19773-9_63","title":"Towards Investigating Performance Differences in Clinical Reasoning in a Technology Rich Learning Environment","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Correctness; Computer science; Metacognition; Artificial intelligence; Human–computer interaction; Cognition; Psychology; 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":[0.003273516,0.0004092043,0.0003340661,0.0007213108,0.0003411012,0.003532766,0.001072919,0.000823941,0.006649303],"category_scores_gemma":[0.01475367,0.0002586897,0.0004380084,0.0008838157,0.0004776913,0.002064533,0.001820194,0.001180574,0.00178043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005785534,"about_ca_system_score_gemma":0.000660744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001334759,"about_ca_topic_score_gemma":0.001649253,"domain_scores_codex":[0.9980739,0.0005648651,0.0001163341,0.0003951155,0.0007079951,0.0001416028],"domain_scores_gemma":[0.9841616,0.01092729,0.001248275,0.000997567,0.001703971,0.0009612456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004485693,0.007920668,0.4066314,0.0008820926,0.0007199735,0.0005597486,0.01820631,0.006116744,0.08715115,0.008800691,0.005572227,0.4529533],"study_design_scores_gemma":[0.00008698693,0.003285214,0.9606858,0.0001178891,0.0001707174,0.0003129334,0.004267845,0.005438826,0.01128639,0.008985376,0.005292474,0.00006955756],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9731221,0.0005197091,0.01023851,0.0002719761,0.00006923829,0.00014488,0.0005256953,0.0001215647,0.01498633],"genre_scores_gemma":[0.9661908,0.0004198222,0.01618907,0.0002001627,0.00003200661,0.0002226497,0.0008276065,0.00007191845,0.01584602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006649303,"threshold_uncertainty_score":0.02224416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05251419946581889,"score_gpt":0.3267423188506005,"score_spread":0.2742281193847816,"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."}}