{"id":"W3217076551","doi":"10.1080/0142159x.2021.1998401","title":"Assessing the predictive validity of the UCAT—A systematic review and narrative synthesis","year":2021,"lang":"en","type":"review","venue":"Medical Teacher","topic":"Medical Education and Admissions","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute for Health and Care Research","keywords":"PsycINFO; Predictive validity; MEDLINE; Predictive power; Psychology; Aptitude; Medical education; Scopus; Clinical psychology; Test (biology); Medicine; Developmental psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003442208,0.0003267501,0.003354109,0.00004114708,0.0002027538,0.0000268585,0.0004160424,0.0003989403,0.01109863],"category_scores_gemma":[0.1319513,0.0001217327,0.0006509339,0.0004824487,0.0005520791,0.00003736167,0.0002010485,0.001514875,0.0000108645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001045465,"about_ca_system_score_gemma":0.004699463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005848161,"about_ca_topic_score_gemma":5.300936e-7,"domain_scores_codex":[0.9936675,0.003376343,0.001148869,0.0003627542,0.001232671,0.0002118232],"domain_scores_gemma":[0.9947056,0.002263593,0.0008022531,0.001040254,0.0001822093,0.001006139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[2.893786e-7,0.0002382592,0.00001087091,0.9305783,0.0005095917,0.00001268456,0.0006898431,1.081749e-9,1.653336e-8,0.00004043272,0.02370041,0.0442193],"study_design_scores_gemma":[0.00005551676,0.00001336372,0.000007547515,0.695676,0.01133209,0.0002787375,0.001049296,0.00001102623,1.667502e-7,0.000006217083,0.2914782,0.00009184112],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004344405,0.9816561,0.00002274839,0.01404122,0.0002987866,0.002176217,0.000005323785,0.00002067415,0.001774617],"genre_scores_gemma":[0.00005659363,0.9927513,0.0000200521,0.002252111,0.000235928,0.0005487603,0.00001629212,0.00003183044,0.004087134],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2677778,"threshold_uncertainty_score":0.9898053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1599666480579051,"score_gpt":0.4724108153925481,"score_spread":0.312444167334643,"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."}}