{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008926777,0.0001868666,0.0002999265,0.0003074734,0.0002100784,0.0001442437,0.0005204664,0.0001245778,0.001020834],"category_scores_gemma":[0.0007936854,0.0001992829,0.00006517499,0.0005867462,0.0000666512,0.001071701,0.00007837977,0.0006000428,0.000007532621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001403595,"about_ca_system_score_gemma":0.002590379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001415086,"about_ca_topic_score_gemma":0.00151661,"domain_scores_codex":[0.9920707,0.004293615,0.0008296034,0.0004777398,0.002035855,0.0002924342],"domain_scores_gemma":[0.997614,0.0005264218,0.0010733,0.0002628347,0.0003990551,0.0001243719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000130208,0.002829759,0.9365988,0.00005067554,0.00003566547,4.481958e-7,0.01832443,0.004735852,0.0002837414,0.02729322,0.0007008898,0.009133476],"study_design_scores_gemma":[0.0008066635,0.00006849294,0.9628106,0.00009641943,0.00005322093,9.463963e-8,0.02418234,0.003776573,0.00001087942,0.002465267,0.005546334,0.0001830833],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9494612,0.000110815,0.000124507,0.03274252,0.001045275,0.001211881,0.000009066344,0.00004966806,0.01524511],"genre_scores_gemma":[0.9918222,0.00004130389,0.006319608,0.0008142819,0.0003940183,0.0002123644,0.0001198742,0.0000209001,0.00025547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04236102,"threshold_uncertainty_score":0.9998924,"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."}}