{"id":"W3194233023","doi":"10.1007/s40692-021-00196-7","title":"Analyzing students’ performance in computerized formative assessments to optimize teachers’ test administration decisions using deep learning frameworks","year":2021,"lang":"en","type":"article","venue":"Journal of Computers in Education","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Test (biology); Cluster analysis; Computer science; Schedule; Psychology; Mathematics education; Artificial intelligence","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":[0.0009563339,0.0001467332,0.0003190683,0.0006314015,0.0001106668,0.0004361539,0.0006486907,0.0001105953,0.000002562317],"category_scores_gemma":[0.0004089876,0.0001527019,0.00007872489,0.00124648,0.00001347469,0.0009963976,0.000195633,0.001041292,0.000002350788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004075722,"about_ca_system_score_gemma":0.0007030278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000391685,"about_ca_topic_score_gemma":0.000006646651,"domain_scores_codex":[0.9980529,0.0002623285,0.000790995,0.0002220978,0.0004407377,0.0002309426],"domain_scores_gemma":[0.9982452,0.0005095394,0.0005361034,0.0002080672,0.0003709104,0.0001301426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001847274,0.001039622,0.2831544,0.00001348558,0.00003107075,0.00003659598,0.007423082,0.5363722,0.0001719683,0.0001485082,0.00003387117,0.1715567],"study_design_scores_gemma":[0.0006422363,0.0002997209,0.1835295,0.001029852,0.00001289539,0.0001144964,0.001108067,0.8125207,0.00006366568,0.000396578,0.000111376,0.0001708965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5023568,0.00004722122,0.4962144,0.0007310877,0.000582131,0.00004415963,7.885129e-8,0.000007539602,0.00001660559],"genre_scores_gemma":[0.5683849,0.00004857168,0.4313153,0.0001325046,0.0000998568,9.715634e-7,0.000002318106,0.000005211835,0.00001028846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2761485,"threshold_uncertainty_score":0.6227005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02118810291347887,"score_gpt":0.3760029940119179,"score_spread":0.3548148910984391,"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."}}