{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03056061,0.0001496708,0.0003809989,0.0009740175,0.0001778882,0.0001525601,0.0007516015,0.00005307499,0.0005150815],"category_scores_gemma":[0.5533034,0.00008913259,0.0001193665,0.001946201,0.00009943532,0.0002297983,0.00009893554,0.0003518991,0.00001520472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002344875,"about_ca_system_score_gemma":0.0006584713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008189293,"about_ca_topic_score_gemma":0.0000262229,"domain_scores_codex":[0.9938505,0.001845697,0.001284473,0.0002780237,0.002413646,0.0003276401],"domain_scores_gemma":[0.7824945,0.2095029,0.001143965,0.0004333998,0.005976571,0.0004487057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008297951,0.0007735586,0.8810499,0.0000113536,0.0000875634,0.00001818726,0.005708713,0.0003041783,0.0008558539,0.00600862,0.001206692,0.1038925],"study_design_scores_gemma":[0.0002291249,0.0001745855,0.9399502,0.0004299094,0.00003981531,0.00009720986,0.003136207,0.00005977749,0.0005320975,0.05482684,0.0004018724,0.0001223458],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5697789,0.001561583,0.4150631,0.006477321,0.003065339,0.000381001,0.00001213186,0.000004992206,0.003655622],"genre_scores_gemma":[0.8300468,0.00001632539,0.1691128,0.0004305319,0.0003407778,0.00001111135,2.269185e-7,0.000006313997,0.00003501343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5227428,"threshold_uncertainty_score":0.9982418,"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."}}