{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.131872,0.001266847,0.00140932,0.005322048,0.00286059,0.007173452,0.006721703,0.004390377,0.001464877],"category_scores_gemma":[0.4549226,0.0007005181,0.001495056,0.004152657,0.02026468,0.004543678,0.005531948,0.01135035,0.001203723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007435801,"about_ca_system_score_gemma":0.017722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008591482,"about_ca_topic_score_gemma":0.01187602,"domain_scores_codex":[0.7660382,0.1080707,0.02415207,0.007046925,0.09323086,0.001461261],"domain_scores_gemma":[0.4551549,0.4063135,0.01276691,0.008524929,0.1127313,0.00450852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003701377,0.0002689642,0.02882258,0.002983872,0.0005598856,0.000713866,0.03194635,0.00260315,0.001755163,0.2041298,0.3118207,0.4140255],"study_design_scores_gemma":[0.0004735043,0.0006163751,0.05149258,0.01136075,0.0003934397,0.003118141,0.0271208,0.0170617,0.007352883,0.5888742,0.2912839,0.0008517536],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.05495706,0.01258073,0.1635793,0.7060983,0.02179427,0.001223881,0.00107033,0.0009865622,0.03770971],"genre_scores_gemma":[0.6292261,0.006576982,0.2114823,0.133868,0.006995075,0.003430706,0.0005640251,0.0005057952,0.007351067],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.131872,"threshold_uncertainty_score":0.6974142,"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."}}