{"id":"W4401975936","doi":"10.1017/iop.2024.10","title":"Selection tests work better than we think they do, and have for years","year":2024,"lang":"en","type":"article","venue":"Industrial and Organizational Psychology","topic":"Medical Education and Admissions","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Selection (genetic algorithm); Psychology; Work (physics); Applied psychology; Computer science; Engineering; Machine learning; Mechanical engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001187997,0.00007156064,0.0001079834,0.00008696139,0.00006275289,0.00003202065,0.00002538065,0.0002063737,0.001563095],"category_scores_gemma":[0.0007221648,0.00005527747,0.00001748197,0.0001930833,0.00005385126,0.00003083504,0.00001188245,0.0002115665,0.00002028344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001216832,"about_ca_system_score_gemma":0.0002060214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002777143,"about_ca_topic_score_gemma":0.000001696646,"domain_scores_codex":[0.9994275,0.00002398846,0.000136127,0.0002187906,0.00008932927,0.0001042501],"domain_scores_gemma":[0.9994863,0.000149264,0.0000198643,0.00005291211,0.00005139131,0.0002402405],"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":[0.0003362252,0.0002617047,0.1442491,0.00006020144,0.0001753118,0.00001721928,0.002409486,6.997508e-7,0.002777101,0.01020802,0.7022224,0.1372826],"study_design_scores_gemma":[0.003708323,0.0005058477,0.1936179,0.0003616228,0.000165789,0.0003777403,0.0002528998,0.00008643408,0.0001908589,0.02327477,0.7772105,0.0002472955],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7071298,0.0009391582,0.0009222376,0.2859565,0.002673871,0.0006860084,0.00003030491,0.0001528123,0.00150933],"genre_scores_gemma":[0.9867142,0.0001233127,0.0006922763,0.006402054,0.002545092,0.00001107983,0.00008194683,0.0000225309,0.003407518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2795844,"threshold_uncertainty_score":0.9993496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06377693491512962,"score_gpt":0.3707149997664763,"score_spread":0.3069380648513467,"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."}}