{"id":"W3049736335","doi":"10.1080/02602938.2020.1805410","title":"Are students gender-neutral in their assessment of online teaching staff?","year":2020,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Workload; Psychology; Construct (python library); Quality (philosophy); Promotion (chess); Medical education; Course evaluation; Higher education; Computer science; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.01188779,0.0002174863,0.0003875306,0.0008850827,0.0005623684,0.00213484,0.0004679922,0.0004108429,0.002285515],"category_scores_gemma":[0.04998548,0.0001871816,0.000372999,0.0004952503,0.001053681,0.001104962,0.0009091743,0.0005160204,0.0008551495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000812918,"about_ca_system_score_gemma":0.0009334445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001750766,"about_ca_topic_score_gemma":0.003225639,"domain_scores_codex":[0.9910017,0.003096901,0.0007761532,0.0008791622,0.003462554,0.0007834911],"domain_scores_gemma":[0.9711277,0.009232206,0.01058547,0.001590982,0.004944581,0.002519157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005359582,0.0002125757,0.8831611,0.0001019607,0.00008693701,0.0002665717,0.01958534,0.0000796188,0.003257644,0.0006307025,0.001297805,0.09078389],"study_design_scores_gemma":[0.00002871917,0.0006124178,0.9557297,0.0001612284,0.00005053854,0.0008136897,0.0321357,0.000485856,0.002832243,0.001347896,0.005738434,0.00006347652],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934933,0.0003078005,0.001288815,0.0008482797,0.00009456572,0.00003440215,0.00009270491,0.00001527276,0.00382499],"genre_scores_gemma":[0.9987356,0.0001053371,0.0002665523,0.0002930152,0.00001747623,0.0000308958,0.00004412904,0.000006247033,0.0005007798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01188779,"threshold_uncertainty_score":0.06286937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3723123297852586,"score_gpt":0.5823678399594441,"score_spread":0.2100555101741854,"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."}}