{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02738014,0.0001825028,0.0004687978,0.0002585207,0.0003808131,0.0004532313,0.002762729,0.00006762052,0.002529213],"category_scores_gemma":[0.06217089,0.0001020644,0.0001949679,0.0004674376,0.0002027671,0.0005500749,0.001062025,0.0001384949,0.000007178061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002942341,"about_ca_system_score_gemma":0.0001156948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005543393,"about_ca_topic_score_gemma":0.0001835619,"domain_scores_codex":[0.995334,0.0005183675,0.002139961,0.0006269544,0.0009790312,0.0004017396],"domain_scores_gemma":[0.9670689,0.02938053,0.001423173,0.001503698,0.0005166376,0.0001070369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007120023,0.0001917843,0.03407185,0.00002027714,0.0001209146,7.51558e-7,0.000153223,0.000003027984,0.001491723,0.00003257293,0.1629221,0.8002797],"study_design_scores_gemma":[0.007521407,0.007244996,0.3044397,0.0008639906,0.0004712732,0.00003863512,0.005628951,0.04791333,0.008940749,0.03587899,0.5803405,0.0007174817],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2046364,0.002483818,0.7454361,0.0105837,0.00634138,0.003323718,0.02708885,0.00003583674,0.00007016923],"genre_scores_gemma":[0.6137658,0.001519694,0.3794474,0.0008184562,0.003406361,0.0001308352,0.0006434798,0.00003462018,0.0002333717],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7995623,"threshold_uncertainty_score":0.9983826,"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."}}