{"id":"W2172179933","doi":"10.1111/emip.12018","title":"Instructional Topics in Educational Measurement (ITEMS) Module: Using Automated Processes to Generate Test Items","year":2013,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Rendering (computer graphics); Test (biology); Item bank; Process (computing); Item response theory; Task (project management); Item analysis; Artificial intelligence; Machine learning; Information retrieval; Psychometrics; Programming language; Psychology; Engineering","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":[0.001455702,0.0002425037,0.0001866668,0.0003161802,0.0003179031,0.0003812745,0.000464349,0.00009852262,0.0001703531],"category_scores_gemma":[0.004121631,0.0002444782,0.00002519468,0.0008894023,0.00005681445,0.001701275,0.0001206347,0.0002243657,0.0001013479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005964222,"about_ca_system_score_gemma":0.002337386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006193183,"about_ca_topic_score_gemma":0.00007027721,"domain_scores_codex":[0.997122,0.0001753803,0.000489036,0.0005947059,0.00128764,0.0003311685],"domain_scores_gemma":[0.9961851,0.0004681657,0.0002313594,0.0003440555,0.002588964,0.0001823385],"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":[0.00009925635,0.01479127,0.1709418,0.0009387482,0.0006787927,0.000007734254,0.007997799,0.007727795,0.05192865,0.5267627,0.1755575,0.04256794],"study_design_scores_gemma":[0.001059022,0.0003262331,0.6858827,0.0006362207,0.00007846624,0.0004206425,0.001321236,0.0189504,0.004005948,0.05083995,0.2349783,0.001500852],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2060344,0.006340825,0.009182005,0.7691264,0.003721789,0.001906059,0.00001380151,0.000329894,0.003344827],"genre_scores_gemma":[0.7649267,0.0001408142,0.2308248,0.001919076,0.0009850654,0.000575269,0.0000200151,0.00001839259,0.0005898114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7672073,"threshold_uncertainty_score":0.9969531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09722074847346185,"score_gpt":0.3606391693617605,"score_spread":0.2634184208882987,"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."}}