{"id":"W2802381110","doi":"10.1007/s40037-018-0425-x","title":"Lies, damned lies, and statistics","year":2018,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Statistics; Data science; Computer science; Medical education; Psychology; Medicine; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002912846,0.0001064753,0.0001924221,0.00007289725,0.0000874997,0.00002080726,0.00005633849,0.0001197627,0.001727943],"category_scores_gemma":[0.1184922,0.00008542604,0.00002658416,0.0001320664,0.0005195484,0.00002628276,0.00002373536,0.0002472953,0.0001662025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008858665,"about_ca_system_score_gemma":0.001064099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001488727,"about_ca_topic_score_gemma":0.00002144499,"domain_scores_codex":[0.9988326,0.00004443598,0.0001916744,0.0003146851,0.000449137,0.0001674829],"domain_scores_gemma":[0.9962685,0.002621848,0.00005524371,0.0002270467,0.0002792854,0.0005480819],"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":[0.0007493022,0.004682801,0.02258961,0.00005880856,0.0001158057,0.00002383067,0.01794583,8.576291e-8,0.00003902544,0.1384399,0.2319057,0.5834493],"study_design_scores_gemma":[0.005374925,0.006772524,0.8328723,0.005012836,0.0003964298,0.0002686393,0.04348963,0.001742221,0.0002905635,0.01701533,0.08606164,0.0007029973],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8928757,0.003444607,0.006028668,0.0446931,0.002149148,0.0006283777,0.00003444036,0.0002157804,0.04993013],"genre_scores_gemma":[0.9810026,0.001225041,0.008629585,0.004974743,0.00187522,0.00002408809,0.00006350313,0.00001875587,0.002186522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8102826,"threshold_uncertainty_score":0.9991846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01499620737032751,"score_gpt":0.3846573583883316,"score_spread":0.3696611510180041,"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."}}