{"id":"W1965259811","doi":"10.1111/j.1468-2389.2009.00451.x","title":"Measurement Reliability, the Spearman–Jensen Effect and the Revised Thorndike Model of Test Bias","year":2009,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Test (biology); Reliability (semiconductor); Statistics; Spearman's rank correlation coefficient; Cognition; Social psychology; Econometrics; 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":[],"consensus_categories":[],"category_scores_codex":[0.00258607,0.00008040255,0.0001542847,0.00006030038,0.00007703398,0.0000545626,0.0001153201,0.00002319596,0.00005260255],"category_scores_gemma":[0.0004697575,0.00004179062,0.0000760417,0.00005960958,0.00008819903,0.00006348148,0.00002464005,0.0002337776,5.338016e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006865307,"about_ca_system_score_gemma":0.00005276926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003614802,"about_ca_topic_score_gemma":0.00000663654,"domain_scores_codex":[0.9987744,0.0002388124,0.0003634871,0.00009720148,0.0004463698,0.00007970942],"domain_scores_gemma":[0.9982474,0.0006609734,0.0003229822,0.00006189515,0.0006764688,0.00003031214],"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":[0.003112838,0.001426023,0.250949,0.00007905024,0.001313235,0.0000218297,0.004905064,0.001744444,0.01635545,0.04354442,0.003799171,0.6727495],"study_design_scores_gemma":[0.01103911,0.003107039,0.9039625,0.0005938058,0.0003971495,0.0009134851,0.001636136,0.04760056,0.00171886,0.02491781,0.003823884,0.000289655],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9710303,0.0005080875,0.003943865,0.01469543,0.0003924121,0.0003059674,0.000003986248,0.000008606773,0.009111354],"genre_scores_gemma":[0.998973,0.0001147311,0.0002922767,0.0003582246,0.0001676667,0.00000373574,3.216123e-7,0.000003806847,0.00008621243],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6724598,"threshold_uncertainty_score":0.1704172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06349361890783131,"score_gpt":0.3763819971673505,"score_spread":0.3128883782595192,"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."}}