{"id":"W6945437321","doi":"10.25384/sage.7105409","title":"Online_Supplement – Supplemental material for The Woodcock-Johnson IV Tests of Achievement Provides Too Many Scores for Clinical Interpretation","year":2018,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Interpretation (philosophy); Test (biology); Stanford–Binet Intelligence Scales; Achievement test; Criterion-referenced test","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001930683,0.0007257056,0.0008801969,0.002684291,0.0006112576,0.001490883,0.001222368,0.001231455,0.7026308],"category_scores_gemma":[0.03010502,0.0004567696,0.0004992989,0.002042404,0.0002219349,0.001216898,0.0008777923,0.001282818,0.2550812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006829072,"about_ca_system_score_gemma":0.001364066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00356106,"about_ca_topic_score_gemma":0.006571003,"domain_scores_codex":[0.9989416,0.0002457589,0.0001889063,0.0001066418,0.000445163,0.00007197782],"domain_scores_gemma":[0.9760248,0.0142626,0.001139392,0.001328204,0.006515735,0.0007292112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009585488,0.0001920797,0.0007881846,0.0002591878,0.00001028235,0.00003411097,0.00001714456,0.00006327856,0.0001778284,0.0003449382,0.9652787,0.03273832],"study_design_scores_gemma":[0.0003150986,0.0004049185,0.02696529,0.001171165,0.00005770311,0.001057533,0.0003174365,0.001151452,0.002351293,0.008110095,0.9579808,0.0001170849],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.009172902,0.00131063,0.01778354,0.006288177,0.005702329,0.001891876,0.8518653,0.009433475,0.09655166],"genre_scores_gemma":[0.04843334,0.003496629,0.06855388,0.01007917,0.004181331,0.006155033,0.655893,0.007188586,0.196019],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7026308,"threshold_uncertainty_score":0.424161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5412988342185119,"score_gpt":0.5631800178181421,"score_spread":0.02188118359963021,"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."}}