{"id":"W2076222948","doi":"10.1080/15305058.2010.509554","title":"Using the Attribute Hierarchy Method to Make Diagnostic Inferences about Examinees’ Knowledge and Skills in Mathematics: An Operational Implementation of Cognitive Diagnostic Assessment","year":2010,"lang":"en","type":"article","venue":"International Journal of Testing","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Advanced Education; University of Alberta","funders":"","keywords":"Cognition; Hierarchy; Set (abstract data type); Item response theory; Test (biology); Computer science; Computerized adaptive testing; Psychology; Psychometrics; Artificial intelligence; Mathematics education; Developmental psychology","routes":{"ca_aff":true,"ca_fund":false,"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":[],"category_scores_codex":[0.001903717,0.0001674974,0.0003165385,0.0002801119,0.00007887088,0.0001151919,0.0003161343,0.00004513674,0.0001267867],"category_scores_gemma":[0.02214393,0.0001201835,0.00005085806,0.0002162159,0.00007663352,0.0002987106,0.0001903634,0.0003140198,0.000001887382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000755612,"about_ca_system_score_gemma":0.0002415251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005645281,"about_ca_topic_score_gemma":0.000309258,"domain_scores_codex":[0.997999,0.0001523667,0.0009584316,0.0001571644,0.0005597034,0.000173327],"domain_scores_gemma":[0.9677132,0.03024636,0.0005387815,0.0000755884,0.001318921,0.0001071119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004551155,0.003681996,0.5980329,0.0002745439,0.0006712045,0.0002164448,0.02538566,0.0001568973,0.03009779,0.05280675,0.00008702031,0.2885433],"study_design_scores_gemma":[0.002092589,0.0005342165,0.7831923,0.003275137,0.0001728875,0.0006734778,0.006940448,0.003876935,0.01222241,0.1866129,0.0000178667,0.0003887695],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9216115,0.00002985819,0.07713275,0.0002368769,0.0001895804,0.0003508194,0.00004144212,0.000006546134,0.0004006037],"genre_scores_gemma":[0.7185038,0.000006388862,0.2812521,0.0000595543,0.0001378511,0.0000148469,0.000005870912,0.00001124806,0.000008382012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2881545,"threshold_uncertainty_score":0.986093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0804734892655436,"score_gpt":0.4593924747952735,"score_spread":0.3789189855297299,"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."}}