{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004928872,0.0003140998,0.0003699955,0.0002219382,0.001095963,0.0005442844,0.0002733595,0.0001716214,0.0002731098],"category_scores_gemma":[0.0005593033,0.0002814831,0.00007119197,0.000956481,0.0002911167,0.001285708,0.00008505065,0.0002791922,0.000005859559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000285084,"about_ca_system_score_gemma":0.001740732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00170083,"about_ca_topic_score_gemma":0.001244925,"domain_scores_codex":[0.9978013,0.00008080061,0.0005198076,0.0004786567,0.0004696132,0.0006498102],"domain_scores_gemma":[0.9977862,0.0006601636,0.0002746643,0.0002298415,0.0002777096,0.0007714297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001660812,0.001812713,0.7734231,0.0005176727,0.0003764262,0.00001160437,0.02464401,0.0002579128,0.0004495361,0.009994125,0.002961072,0.1853858],"study_design_scores_gemma":[0.003684344,0.005638506,0.7020515,0.0003615145,0.000912362,0.00005662114,0.1241786,0.1293312,0.0001182724,0.004290207,0.02722684,0.002149994],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926506,0.0002361445,0.002000113,0.002476733,0.0003036898,0.001157753,0.0001334321,0.0001462679,0.0008952359],"genre_scores_gemma":[0.9795246,0.0003455419,0.01741671,0.001747534,0.0004794217,0.0001474625,0.0001505975,0.00003839084,0.0001497424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1832358,"threshold_uncertainty_score":0.9999638,"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."}}