{"id":"W3107092920","doi":"10.5753/cbie.sbie.2020.51","title":"Online assessments with parametric questions and automatic corrections: an improvement for MCTest using Google Forms and Sheets","year":2020,"lang":"en","type":"article","venue":"Anais do XXXI Simpósio Brasileiro de Informática na Educação (SBIE 2020)","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo; Canadian Bureau for International Education","keywords":"Python (programming language); Computer science; Parametric statistics; Class (philosophy); Coronavirus disease 2019 (COVID-19); Web application; World Wide Web; Multimedia; Programming language; Artificial intelligence; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009119634,0.002257237,0.001553249,0.003784782,0.0005810293,0.003745739,0.002977194,0.001347077,0.01746134],"category_scores_gemma":[0.04264605,0.0008286597,0.001342439,0.002187194,0.0006294571,0.003954891,0.004121515,0.002061622,0.0154862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004184178,"about_ca_system_score_gemma":0.002084675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001452547,"about_ca_topic_score_gemma":0.001277767,"domain_scores_codex":[0.9829444,0.006556394,0.001742752,0.002247824,0.005950538,0.0005580217],"domain_scores_gemma":[0.9605083,0.01385464,0.002118891,0.01057104,0.01117746,0.001769726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008499084,0.001037411,0.006298272,0.000780777,0.0001133476,0.0004342928,0.00134856,0.002049109,0.0189677,0.001432717,0.02164773,0.9450401],"study_design_scores_gemma":[0.001252945,0.003726502,0.1056904,0.002321266,0.0007131762,0.006491058,0.004000547,0.1645787,0.1138673,0.01920684,0.5769838,0.001167496],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08588573,0.0006658559,0.7674063,0.001767283,0.0007060173,0.003353326,0.003292327,0.1244664,0.0124567],"genre_scores_gemma":[0.1676139,0.0003480651,0.8049809,0.0004048166,0.0002844522,0.001534854,0.004093896,0.00727541,0.01346371],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01746134,"threshold_uncertainty_score":0.05841398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0699111291880333,"score_gpt":0.4188639497343912,"score_spread":0.3489528205463579,"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."}}