{"id":"W2557191358","doi":"10.1177/0734282916678336","title":"A Systematic Examination of the Linguistic Demand of Cognitive Test Directions Administered to School-Age Populations","year":2016,"lang":"en","type":"article","venue":"Journal of Psychoeducational Assessment","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Test (biology); Cognition; Cognitive test; Norm-referenced test; Wechsler Adult Intelligence Scale; Intelligence quotient; Cognitive psychology; Standardized test; Developmental psychology; Linguistics; Achievement test; Mathematics education","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":[0.00108601,0.0001707377,0.0004127746,0.0003170911,0.0001116855,0.00002047116,0.0003942589,0.00007951303,0.00129968],"category_scores_gemma":[0.002395211,0.00009627324,0.0002330172,0.0005803959,0.0001118973,0.0001021139,0.00003197623,0.0001768842,0.00003456231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000187513,"about_ca_system_score_gemma":0.0004314278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001317684,"about_ca_topic_score_gemma":0.0000115996,"domain_scores_codex":[0.9970254,0.0004908506,0.001408936,0.0002246098,0.0006724227,0.0001777226],"domain_scores_gemma":[0.9941755,0.002373122,0.001594913,0.0003145458,0.001348371,0.0001935554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004263989,0.02730853,0.7908471,0.002097547,0.002278625,0.00001284903,0.01444208,0.00002966055,0.01398821,0.1218056,0.0198095,0.006953901],"study_design_scores_gemma":[0.0007428621,0.00050216,0.9873632,0.003795767,0.0002034823,0.00006579421,0.001619508,0.000001090148,0.00007296588,0.005250225,0.0002674696,0.0001154568],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9584923,0.0002959998,0.005690772,0.006858853,0.006083671,0.001061089,0.0001739412,0.00001019446,0.02133315],"genre_scores_gemma":[0.9927949,0.00001127556,0.002809279,0.0002294667,0.0004212045,0.0001349501,0.00000826792,0.00001490219,0.003575746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1965161,"threshold_uncertainty_score":0.9996133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08049613797855797,"score_gpt":0.4503819937754389,"score_spread":0.3698858557968809,"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."}}