{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02166215,0.001594166,0.0008297944,0.008744,0.001098137,0.002780881,0.002410192,0.001293442,0.005014341],"category_scores_gemma":[0.1421246,0.0008711764,0.0008200251,0.006215573,0.002239584,0.00538716,0.00387213,0.001748793,0.002122759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002414093,"about_ca_system_score_gemma":0.003472753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002497402,"about_ca_topic_score_gemma":0.002335734,"domain_scores_codex":[0.964789,0.02402358,0.001825621,0.00189005,0.00679339,0.0006783633],"domain_scores_gemma":[0.8414865,0.09835453,0.005919343,0.02414146,0.02929765,0.0008005316],"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":[0.0004073208,0.0005373369,0.00932591,0.0003725198,0.00007171881,0.0002735684,0.005426471,0.01349019,0.01270761,0.03092852,0.007448472,0.9190105],"study_design_scores_gemma":[0.0005735686,0.001322957,0.01724971,0.001345231,0.0002111162,0.001739239,0.00465563,0.6126176,0.1199484,0.1957179,0.04412873,0.0004900161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02359413,0.00007308664,0.9678366,0.0002924534,0.0000573248,0.001125143,0.0001465114,0.003626864,0.003247852],"genre_scores_gemma":[0.09366827,0.00007633987,0.9029536,0.0001048673,0.00002230657,0.0009205866,0.0004081427,0.0005137009,0.001332114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02166215,"threshold_uncertainty_score":0.1145617,"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."}}