{"id":"W4251534070","doi":"10.32920/ryerson.14637987","title":"Assessing semester-long student team design reports in large classes to provide individual student grades.","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Engineering Education and Pedagogy","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Rubric; Grading (engineering); Workload; Documentation; Teamwork; Computer science; Mathematics education; Engineering management; Psychology; Engineering","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00103894,0.0005629594,0.0006559239,0.0005483194,0.00005113442,0.00120788,0.0004585552,0.0003804307,0.0001254106],"category_scores_gemma":[0.0001069218,0.0006140139,0.0001298809,0.0003520379,0.00001084432,0.0002798745,0.0007132689,0.001079842,0.0000110513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005481039,"about_ca_system_score_gemma":0.0004615037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006953848,"about_ca_topic_score_gemma":0.000531848,"domain_scores_codex":[0.9967705,0.0001279509,0.001001658,0.0007741641,0.0006743898,0.0006513341],"domain_scores_gemma":[0.9985088,0.000141154,0.0001165757,0.0008650107,0.0001005978,0.0002678411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.000002211324,0.0007111965,0.1463802,0.0009800515,0.000382365,0.000696575,0.01594974,0.8251575,0.0005061331,0.00004093874,0.006210058,0.002983015],"study_design_scores_gemma":[0.0005079298,0.00005962859,0.9684172,0.001522479,0.0001439778,0.0001475865,0.01133478,0.003969019,0.002912026,0.00003696919,0.009126404,0.001822003],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8607965,0.001048276,0.1288775,0.0002043394,0.004509044,0.001415133,0.000007314834,0.0008654971,0.002276464],"genre_scores_gemma":[0.9812562,0.00008988842,0.0167233,0.0001979856,0.0002825547,0.0005255125,0.0001504906,0.0001385281,0.0006355072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.822037,"threshold_uncertainty_score":0.9998289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06195946985514941,"score_gpt":0.3735138908860698,"score_spread":0.3115544210309203,"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."}}