{"id":"W7042390486","doi":"","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":"W&M Publish (College of William & Mary)","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":[0.001767392,0.0008132895,0.0009588599,0.00266766,0.0006757022,0.001541591,0.001335368,0.001295307,0.7298605],"category_scores_gemma":[0.02450329,0.0004961615,0.0005422806,0.001985244,0.000210944,0.001244632,0.0009346673,0.001257383,0.2671963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007264816,"about_ca_system_score_gemma":0.001376756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004295846,"about_ca_topic_score_gemma":0.00809579,"domain_scores_codex":[0.9990575,0.0002045396,0.0001573318,0.0001009381,0.0004054332,0.00007432758],"domain_scores_gemma":[0.9817442,0.0100298,0.0008954747,0.001067959,0.005606042,0.0006566189],"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":[0.00008649906,0.0001867149,0.0006699257,0.0002310128,0.000009666536,0.0000320738,0.00001451127,0.00006356047,0.0001696772,0.0003085559,0.9694628,0.02876496],"study_design_scores_gemma":[0.0003498964,0.0004039904,0.02679368,0.001049541,0.00006183099,0.001024357,0.0002906118,0.001350822,0.00229364,0.007520523,0.9587384,0.0001226458],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.008276721,0.001291881,0.01684408,0.005459438,0.00610036,0.001932961,0.853122,0.008858873,0.09811365],"genre_scores_gemma":[0.04293712,0.003453779,0.06307478,0.008786818,0.004049941,0.005913627,0.662329,0.006449043,0.2030059],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7298605,"threshold_uncertainty_score":0.3853212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2235703051651677,"score_gpt":0.4593674683569391,"score_spread":0.2357971631917714,"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."}}