{"id":"W2146894730","doi":"10.1111/j.1745-3984.2011.00142.x","title":"Using the Attribute Hierarchy Method to Make Diagnostic Inferences about Examinees’ Cognitive Skills in Critical Reading","year":2011,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Cognition; Reading (process); Psychology; Reading comprehension; Set (abstract data type); Test (biology); Sample (material); Cognitive psychology; Hierarchy; Comprehension; Natural language processing; Computer science; Artificial intelligence; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02750866,0.00070694,0.0005801899,0.007300245,0.0009026969,0.001501422,0.0008959151,0.0006487184,0.001706337],"category_scores_gemma":[0.1561389,0.0003806228,0.0008458025,0.00343336,0.00105243,0.002847646,0.002113256,0.001489539,0.0003360336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007873774,"about_ca_system_score_gemma":0.001360202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003685861,"about_ca_topic_score_gemma":0.003990437,"domain_scores_codex":[0.9807233,0.01271524,0.001544718,0.001073845,0.00357627,0.0003665242],"domain_scores_gemma":[0.8633758,0.1120493,0.007571429,0.007722528,0.008312535,0.0009683975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009178545,0.0006146923,0.5174929,0.0004183814,0.0004396198,0.0003045912,0.01340887,0.01012385,0.006253977,0.01928587,0.00266322,0.4280763],"study_design_scores_gemma":[0.0004324087,0.002032999,0.4664549,0.00063933,0.0004621661,0.002257249,0.01223818,0.3471308,0.01696848,0.1421456,0.008839974,0.0003978748],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5181855,0.0002239227,0.4738452,0.000333885,0.00007915948,0.0007196076,0.0004571902,0.000592844,0.005562588],"genre_scores_gemma":[0.7599263,0.00009530682,0.2387074,0.00005409036,0.00002480349,0.0005987055,0.0002665868,0.00003863987,0.0002881046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02750866,"threshold_uncertainty_score":0.1454815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7841432219145653,"score_gpt":0.5727164674921034,"score_spread":0.2114267544224619,"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."}}