{"id":"W2531128920","doi":"10.1037/cbs0000057","title":"Working memory assessment: Construct validity of the Brown-Peterson Test.","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Behavioural Science/Revue canadienne des sciences du comportement","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Construct validity; Construct (python library); Test (biology); Test validity; Validation test; Memory test; Psychometrics; Social psychology; Cognitive psychology; Developmental psychology; Cognition","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00348975,0.0002032807,0.0003116775,0.0004610977,0.001243681,0.000121854,0.002031256,0.00006134805,0.00200907],"category_scores_gemma":[0.0002269304,0.0001151134,0.0001869121,0.001385909,0.00707861,0.0004190493,0.00006051654,0.0002260857,0.000006370314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001346861,"about_ca_system_score_gemma":0.003004184,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01924742,"about_ca_topic_score_gemma":0.09015912,"domain_scores_codex":[0.9971671,0.000172829,0.0008100351,0.0004238633,0.0004603451,0.0009658966],"domain_scores_gemma":[0.9967587,0.000274445,0.0008995155,0.0003534727,0.0005007943,0.001213092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002768436,0.0000717138,0.9818834,0.000003320737,0.00001245492,0.00005932009,0.001179435,0.000005591619,0.001663205,0.006009879,0.0005375025,0.008571391],"study_design_scores_gemma":[0.0004191746,0.0005264791,0.9911814,0.0002463585,0.00003984593,0.0006775234,0.00226587,0.00000793271,0.0002392504,0.002941798,0.0012641,0.0001903054],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9812998,0.00007839898,0.00006917794,0.002866766,0.006162153,0.0002062867,0.00003848247,0.000004914566,0.00927404],"genre_scores_gemma":[0.9981231,0.000004218384,0.0009682631,0.0002307813,0.0001609611,0.000007704271,6.549469e-7,0.000007189272,0.0004971015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0709117,"threshold_uncertainty_score":0.9989032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2108126551231498,"score_gpt":0.3417568452108298,"score_spread":0.13094419008768,"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."}}