{"id":"W2092367835","doi":"10.1109/te.2011.2160946","title":"A Control Systems Concept Inventory Test Design and Assessment","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Education","topic":"Experimental Learning in Engineering","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Concept inventory; Test (biology); Consistency (knowledge bases); Computer science; Classical test theory; Item response theory; Test design; Test theory; Control (management); Internal consistency; Multiple choice; Test score; Mathematics education; Test method; Artificial intelligence; Psychology; Psychometrics; Mathematics; Standardized test; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005722919,0.0008682999,0.0008153209,0.002437168,0.0004292893,0.001004928,0.001385911,0.0007367283,0.004327565],"category_scores_gemma":[0.01494194,0.000531574,0.001019375,0.001160959,0.0004423336,0.001044984,0.001230112,0.00113239,0.001889435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007223309,"about_ca_system_score_gemma":0.002198121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001086284,"about_ca_topic_score_gemma":0.00118304,"domain_scores_codex":[0.9949358,0.001273508,0.001004612,0.0002742351,0.002295506,0.0002163482],"domain_scores_gemma":[0.9888452,0.0039426,0.0009369042,0.0004361088,0.005331573,0.0005076058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002902521,0.005009638,0.2550659,0.0008215312,0.0002432691,0.0003410279,0.0008819579,0.01201339,0.0179917,0.004462298,0.01187545,0.6883913],"study_design_scores_gemma":[0.001814215,0.02279604,0.7676992,0.0004524782,0.0002940897,0.001833584,0.0009120657,0.08959801,0.05094425,0.00513001,0.05816564,0.0003604066],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6759487,0.0007832777,0.240669,0.0008055425,0.0004226942,0.0385099,0.007352349,0.002052051,0.03345636],"genre_scores_gemma":[0.594023,0.0006638428,0.3185534,0.0004790951,0.0001322915,0.06126283,0.01174236,0.0002980355,0.01284512],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005722919,"threshold_uncertainty_score":0.03026611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01944075689435389,"score_gpt":0.245397405439759,"score_spread":0.2259566485454051,"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."}}