{"id":"W2109920068","doi":"10.1080/08957347.2014.905787","title":"Testing Expert-Based Versus Student-Based Cognitive Models for a Grade 3 Diagnostic Mathematics Assessment","year":2014,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Medical Council of Canada; University of Alberta","funders":"","keywords":"Cognition; Psychology; Test (biology); Consistency (knowledge bases); Construct (python library); Cognitive test; Cognitive psychology; Statistics; Artificial intelligence; Computer science; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001295043,0.0002629938,0.0002587121,0.0001695115,0.0001315111,0.00005266006,0.0002411863,0.0001197593,0.0001235269],"category_scores_gemma":[0.0005093385,0.0002513474,0.00006603919,0.0003135667,0.00004841842,0.00005624059,0.00001305043,0.0001806728,0.00004684719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004200838,"about_ca_system_score_gemma":0.0004521378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005562872,"about_ca_topic_score_gemma":0.00002090272,"domain_scores_codex":[0.9977715,0.0001417622,0.0005010576,0.0005470612,0.0006419721,0.0003966288],"domain_scores_gemma":[0.9957211,0.003207605,0.0002587611,0.0003149395,0.0003749218,0.0001226806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001495234,0.1102479,0.07636062,0.0007610318,0.0006306461,0.000001794093,0.01429826,0.007391716,0.009007501,0.4007683,0.01364861,0.3653884],"study_design_scores_gemma":[0.0332235,0.002544886,0.7977805,0.001513208,0.0005319374,0.000002162036,0.03865654,0.01429783,0.00156852,0.1031844,0.00432783,0.002368664],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5986949,0.0003534977,0.2907467,0.002763523,0.006284835,0.00650803,0.00003065722,0.0002261024,0.09439171],"genre_scores_gemma":[0.9553943,0.000001307105,0.03384065,0.001250344,0.0003034387,0.008989414,0.0001553802,0.00003565005,0.00002956484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7214199,"threshold_uncertainty_score":0.9999939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2185151809927274,"score_gpt":0.4421785572880547,"score_spread":0.2236633762953272,"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."}}