{"id":"W2548734396","doi":"10.5296/jei.v2i2.10040","title":"A Model-Based Method for Content Validation of Automatically Generated Test Items","year":2016,"lang":"en","type":"article","venue":"Journal of Educational Issues","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Computer science; Content (measure theory); Item bank; Item response theory; Information retrieval; Graph; Natural language processing; Artificial intelligence; Data mining; Statistics; Mathematics; Theoretical computer science; Psychometrics","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":[0.0139359,0.001862974,0.0009942306,0.004383897,0.001051443,0.002033422,0.00260144,0.001679449,0.004871882],"category_scores_gemma":[0.08450373,0.0009944201,0.001685475,0.002204446,0.001078942,0.001934297,0.001924576,0.003091699,0.002256554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001904613,"about_ca_system_score_gemma":0.003051304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007214903,"about_ca_topic_score_gemma":0.00812469,"domain_scores_codex":[0.985132,0.008282899,0.0008877808,0.00183507,0.003650847,0.0002113332],"domain_scores_gemma":[0.9471823,0.0350853,0.001868058,0.00676263,0.008880486,0.0002212763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004355061,0.0007287497,0.005568341,0.000697051,0.0005193845,0.0002926074,0.001497416,0.1085785,0.01811952,0.02776602,0.009047844,0.826749],"study_design_scores_gemma":[0.0001959105,0.0002498544,0.002561542,0.0001670352,0.0001140853,0.0002325878,0.0001855114,0.9507983,0.01541699,0.02099822,0.008980702,0.0000993223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002237638,0.00001537555,0.9945822,0.0000318656,0.0000182234,0.0003128062,0.0001476976,0.002331745,0.0003223903],"genre_scores_gemma":[0.04270328,0.00002462816,0.9540484,0.00005139788,0.000008971137,0.001368463,0.0008366762,0.0004842797,0.0004738737],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0139359,"threshold_uncertainty_score":0.07370102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1028713208901992,"score_gpt":0.3784143698961985,"score_spread":0.2755430490059992,"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."}}