{"id":"W2095690048","doi":"10.22329/il.v34i4.4141","title":"Critique of the Watson-Glaser Critical Thinking Appraisal Test: The More You Know, the Lower Your Score","year":2014,"lang":"en","type":"article","venue":"Informal Logic","topic":"Education and Critical Thinking Development","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Watson; Promotion (chess); Construct (python library); Psychology; Construct validity; Critical appraisal; Government (linguistics); Social psychology; Psychometrics; Computer science; Clinical psychology; Medicine; Artificial intelligence; Law; Political science; Alternative medicine; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002290601,0.0001404295,0.0001419566,0.00002389429,0.001611166,0.0001962167,0.001095467,0.0001357128,0.0003673909],"category_scores_gemma":[0.008188447,0.00006305044,0.0001345946,0.0003005116,0.001528544,0.0002487635,0.0002070372,0.0004708593,0.00007935536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003429926,"about_ca_system_score_gemma":0.0003236482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001832577,"about_ca_topic_score_gemma":0.0001166489,"domain_scores_codex":[0.9980428,0.0002352681,0.0003493097,0.0001447236,0.0007700915,0.0004578427],"domain_scores_gemma":[0.996999,0.002174587,0.00007373901,0.0003738101,0.0002791168,0.00009976625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006084282,0.00009981759,0.005197774,0.00001794494,0.000007518905,6.669127e-7,0.03415034,0.0000113876,0.000007103012,0.9541619,0.003450673,0.002888804],"study_design_scores_gemma":[0.0002825302,0.0001448283,0.05678589,0.0002115905,0.00005420779,0.00001488737,0.04534214,0.0002951043,0.0003213699,0.1744576,0.7216832,0.0004065993],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1689907,0.0002415884,0.001666811,0.4207779,0.00595209,0.0008579553,0.00001547529,0.0002296058,0.4012679],"genre_scores_gemma":[0.9815895,0.00002180102,0.0004189926,0.01611168,0.0004742775,0.00003357094,0.000001853253,0.000008379218,0.001339951],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8125988,"threshold_uncertainty_score":0.9996886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03291475972431309,"score_gpt":0.3555261938659,"score_spread":0.3226114341415869,"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."}}