{"id":"W6977184349","doi":"10.6084/m9.figshare.17071985","title":"Assessing the predictive validity of the UCAT—A systematic review and narrative synthesis","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Predictive power; Predictive validity; Aptitude; Cognition; Univariate; Inclusion (mineral); Predictive value; Narrative","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002591679,0.00007550918,0.0002732088,0.0000119301,0.0002065943,0.000177835,0.0006375594,0.00002171545,0.001461816],"category_scores_gemma":[0.006456636,0.00003751983,0.0000876712,0.000422926,0.00001215861,0.0002969237,0.0004245015,0.00008537775,0.00001856845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001250778,"about_ca_system_score_gemma":0.000107744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002122404,"about_ca_topic_score_gemma":0.000002037722,"domain_scores_codex":[0.9988084,0.0005291707,0.0001898975,0.0001926115,0.000196162,0.0000837541],"domain_scores_gemma":[0.9979798,0.0008731771,0.0002175084,0.0007296929,0.000175596,0.00002420482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","study_design_scores_codex":[5.973612e-7,0.0001795072,0.000381704,0.4824807,0.0010682,0.00004261417,0.01423038,0.00004364473,0.000133479,0.0004712295,0.4980552,0.002912688],"study_design_scores_gemma":[0.0001146016,0.00003331936,0.009353738,0.9507367,0.001815866,0.0001430159,0.005187902,0.02261134,0.007453638,0.00029834,0.001770157,0.0004813866],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.007162863,0.4625925,0.01020371,0.07105341,0.001087632,0.008790042,0.4189349,0.0009725647,0.01920232],"genre_scores_gemma":[0.9947887,0.0002755997,0.0009399109,0.00152971,0.00005720746,0.000701655,0.001363106,0.00001380866,0.0003303036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9876258,"threshold_uncertainty_score":0.999451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0728562355696405,"score_gpt":0.3074778021648811,"score_spread":0.2346215665952406,"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."}}