{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01333076,0.0002916479,0.0007796302,0.000534495,0.0003039255,0.0002523902,0.001794304,0.0001412169,0.001037913],"category_scores_gemma":[0.04647562,0.0001833118,0.0004713912,0.001170022,0.0005477538,0.000767906,0.0005704599,0.0001289083,0.000003878551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000645967,"about_ca_system_score_gemma":0.0002335825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001084491,"about_ca_topic_score_gemma":0.0002274314,"domain_scores_codex":[0.9943252,0.0004340123,0.002620381,0.0008112697,0.001252383,0.0005567755],"domain_scores_gemma":[0.9733208,0.02268488,0.001523506,0.0009463867,0.001393656,0.0001307786],"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":[0.001734468,0.0005724455,0.06368154,0.0001002755,0.0001828531,8.272565e-7,0.000197878,0.000006851315,0.0007020051,0.001826242,0.8329794,0.09801518],"study_design_scores_gemma":[0.005983474,0.007844818,0.2455304,0.0001608626,0.0002222053,0.00000509575,0.003023367,0.008597123,0.006379896,0.0250108,0.6966804,0.0005615549],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8453491,0.000332019,0.102046,0.01477419,0.0121467,0.008675901,0.01534788,0.0001068487,0.001221386],"genre_scores_gemma":[0.8040252,0.00005925411,0.1920645,0.0004540083,0.001424828,0.0004639127,0.0002231901,0.00004080003,0.001244379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1818489,"threshold_uncertainty_score":0.9998752,"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."}}