{"id":"W4225425474","doi":"10.3389/feduc.2022.853578","title":"Using Content Coding and Automatic Item Generation to Improve Test Security","year":2022,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Coding (social sciences); Scalability; Item bank; Process (computing); Data mining; Item response theory; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0003694181,0.00006842709,0.00008763158,0.0002100778,0.0001860147,0.00009374252,0.0001922014,0.0000186846,0.000001801601],"category_scores_gemma":[0.0004140159,0.00007964847,0.00001179899,0.0003223546,0.00001039841,0.0001904778,0.000147148,0.0000933643,3.495839e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000334138,"about_ca_system_score_gemma":0.0001460667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000177523,"about_ca_topic_score_gemma":0.000002558287,"domain_scores_codex":[0.9992914,0.00006216854,0.0001520896,0.000242158,0.0001302308,0.0001219867],"domain_scores_gemma":[0.9995627,0.00006964067,0.00006841696,0.0002132106,0.00004009786,0.00004587451],"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":[0.000003464203,0.0004658895,0.3048342,0.00007083547,0.000009147523,0.0000032631,0.01350284,0.0003215011,0.00776818,0.001983153,0.152959,0.5180786],"study_design_scores_gemma":[0.00008760216,0.00007865659,0.00689093,0.00002991766,0.000003879574,0.00001632893,0.0003118079,0.9812683,0.0007619265,0.009966576,0.000438735,0.0001453019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.427594,0.0002329133,0.5678958,0.0005670426,0.002471559,0.0003009906,0.000002108219,0.0008852091,0.00005038195],"genre_scores_gemma":[0.6063846,0.000001894757,0.3931284,0.0003254889,0.00004897363,0.00007782604,0.00000308576,0.000004299614,0.00002543109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9809468,"threshold_uncertainty_score":0.324797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04183309971773125,"score_gpt":0.2869789934573029,"score_spread":0.2451458937395716,"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."}}