{"id":"W4389915531","doi":"10.21449/ijate.1321061","title":"A data pipeline for e-large-scale assessments: Better automation, quality assurance, and efficiency","year":2023,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Mental Health Research Topics","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Northern Alberta Institute of Technology","funders":"International Atomic Energy Agency","keywords":"Workflow; Computer science; Pipeline (software); Scale (ratio); Quality assurance; Automation; Interface (matter); Quality (philosophy); Data science; Data quality; Risk analysis (engineering); Data mining; Database; Engineering; Operations management; Metric (unit)","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":[0.04225607,0.002302454,0.001589155,0.005623942,0.00172232,0.009209383,0.003838272,0.001631485,0.01599478],"category_scores_gemma":[0.1215481,0.002291063,0.00202511,0.005277465,0.001507176,0.01128094,0.007990595,0.004801682,0.01468649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002145598,"about_ca_system_score_gemma":0.01056926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006779331,"about_ca_topic_score_gemma":0.003633433,"domain_scores_codex":[0.976834,0.008532993,0.003414843,0.003181518,0.007053092,0.0009835496],"domain_scores_gemma":[0.8532255,0.05763989,0.005471448,0.04790611,0.02960117,0.00615594],"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":[0.001926159,0.0009685775,0.01268362,0.001589835,0.0001960003,0.0007173375,0.004249562,0.00633816,0.02394388,0.02183838,0.1317552,0.7937933],"study_design_scores_gemma":[0.001488392,0.001234634,0.02716717,0.002078613,0.0002112822,0.001311638,0.002438376,0.1525518,0.07341775,0.1025124,0.6345035,0.001084316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00822758,0.0003268496,0.8860238,0.003246181,0.000282909,0.003309236,0.006168782,0.088494,0.003920744],"genre_scores_gemma":[0.04205591,0.0003253834,0.933937,0.000795547,0.0001488276,0.002067002,0.01051835,0.00758466,0.002567337],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04225607,"threshold_uncertainty_score":0.2234741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1654467129443049,"score_gpt":0.5848930899388985,"score_spread":0.4194463769945936,"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."}}