{"id":"W2483081267","doi":"10.4018/978-1-4666-9441-5.ch022","title":"Using Automated Procedures to Generate Test Items That Measure Junior High Science Achievement","year":2015,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Section (typography); Computer science; Test (biology); Quality (philosophy); Measure (data warehouse); Curriculum; Mathematics education; Data mining; Psychology; Pedagogy","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005155001,0.0004120804,0.0003124949,0.0005943051,0.0005315539,0.000138309,0.0007960458,0.0002112153,0.00009768339],"category_scores_gemma":[0.00004382594,0.0003617647,0.00002053011,0.000298686,0.0002886468,0.002147222,0.0005092939,0.0003280248,0.00002905377],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005866571,"about_ca_system_score_gemma":0.007776845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003450354,"about_ca_topic_score_gemma":0.00002039067,"domain_scores_codex":[0.9974717,0.00002916786,0.0004702939,0.0008303495,0.0008344104,0.0003641056],"domain_scores_gemma":[0.9985298,0.0000743027,0.0003061509,0.0003654296,0.0005039864,0.000220338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002349889,0.00033951,0.002532217,0.0001820377,0.00002418578,0.000004032485,0.001212275,0.00006983877,0.0003840507,0.9763348,0.007004298,0.01188932],"study_design_scores_gemma":[0.0001984119,0.00006527494,0.01531384,0.001507104,0.000008979681,0.00002113882,0.0001327081,0.00002693061,0.001301445,0.03431255,0.9464131,0.0006985415],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.03164714,0.2138523,0.00290672,0.1748411,0.1198573,0.01366146,0.0001439008,0.005299982,0.4377901],"genre_scores_gemma":[0.0373831,0.001068973,0.1439904,0.00252325,0.0002419587,0.0004719894,0.00007936901,0.00004603501,0.8141949],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9420222,"threshold_uncertainty_score":0.9998834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06464199464959075,"score_gpt":0.3595467430617855,"score_spread":0.2949047484121948,"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."}}