{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0192246,0.001156924,0.0007729111,0.006422778,0.0009553578,0.002892227,0.001351175,0.0005263512,0.008470004],"category_scores_gemma":[0.07794955,0.0004200663,0.0005045307,0.002820752,0.0003506697,0.001876129,0.002484104,0.001080716,0.005324464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009844661,"about_ca_system_score_gemma":0.001847661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001071318,"about_ca_topic_score_gemma":0.002980433,"domain_scores_codex":[0.9817949,0.007295665,0.002108725,0.002056751,0.006325422,0.0004186333],"domain_scores_gemma":[0.8873398,0.029542,0.01744068,0.01208636,0.04912534,0.004465902],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003797279,0.001082365,0.03540444,0.0004146055,0.0001004391,0.0000796751,0.005931905,0.001551269,0.009008213,0.001357181,0.01659513,0.9280951],"study_design_scores_gemma":[0.0005561245,0.008088116,0.5204191,0.001470191,0.0003300843,0.001353696,0.02141366,0.03801074,0.0940207,0.0141724,0.2993531,0.0008120453],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4886032,0.0007495649,0.4203747,0.0008087222,0.001232955,0.003691362,0.0033731,0.01333243,0.0678339],"genre_scores_gemma":[0.6278907,0.0004590713,0.3326585,0.0001695725,0.0002297735,0.002385642,0.003235268,0.001535992,0.03143547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9807754,"threshold_uncertainty_score":0.1016706,"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."}}