{"id":"W2752299099","doi":"10.1139/cjp-2017-0030","title":"The challenges of changing teaching assistants’ grading practices: Requiring students to show evidence of understanding","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Physics","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rubric; Grading (engineering); Explication; Teaching method; Higher education; Curriculum; Syllabus","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01476249,0.0001038269,0.0002737029,0.0002029547,0.002962611,0.0003337536,0.001437335,0.00004673338,0.000002494963],"category_scores_gemma":[0.01332459,0.00008809355,0.00009157656,0.0001915194,0.00039317,0.001088499,0.00007138323,0.0004799896,4.124719e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007745881,"about_ca_system_score_gemma":0.001014151,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006308726,"about_ca_topic_score_gemma":0.03016092,"domain_scores_codex":[0.9976346,0.0007499764,0.0004029939,0.0001204037,0.000664471,0.000427483],"domain_scores_gemma":[0.9953192,0.00125162,0.002511733,0.0003198874,0.0003452637,0.0002522437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002275631,0.00001687561,0.03363237,0.00006453662,0.0001377602,0.0000216172,0.1200189,0.0000367887,0.002773228,0.8167927,0.00006262722,0.02641989],"study_design_scores_gemma":[0.001018831,0.0007934907,0.06534913,0.01730073,0.0003383968,0.00002224886,0.7358052,0.0001158823,0.006614901,0.166304,0.005333776,0.001003491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9192318,0.001702762,0.04863175,0.01128215,0.002347715,0.000330687,0.000005190826,0.000009742767,0.01645823],"genre_scores_gemma":[0.9963945,0.00009694425,0.002909976,0.00002898587,0.0004984338,8.510937e-7,2.834162e-8,0.00001420232,0.00005603962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6504887,"threshold_uncertainty_score":0.9983354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4454470432084531,"score_gpt":0.4956241653859584,"score_spread":0.05017712217750536,"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."}}