{"id":"W4250079707","doi":"10.14293/s2199-1006.1.sor-.pputigr.v1","title":"Small samples, unreasonable generalizations, and outliers: Gender bias in student evaluation of teaching or three unhappy students?","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Teacher Professional Development and Motivation","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Royal University","funders":"","keywords":"Psychology; Gender bias; Outlier; Set (abstract data type); Sample (material); Social psychology; Section (typography); Statistics; Mathematics; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.006852613,0.000217483,0.0003397208,0.0002050383,0.0002752355,0.0001506693,0.0004663023,0.000278773,0.0003504063],"category_scores_gemma":[0.001235261,0.0001852953,0.00004920193,0.00022692,0.00007514664,0.0001544322,0.0007434311,0.0004493001,0.000003232719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004669344,"about_ca_system_score_gemma":0.001368661,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.007052322,"about_ca_topic_score_gemma":0.01882619,"domain_scores_codex":[0.9956279,0.00129433,0.0005728609,0.0005171312,0.001742639,0.00024516],"domain_scores_gemma":[0.998876,0.0002061957,0.0003302257,0.0001823916,0.0002967335,0.0001084028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002764638,0.0002543582,0.90087,0.00008593799,0.0001134399,0.000001078443,0.05985973,0.0004034981,0.00002786962,0.02395931,0.0007697283,0.01362735],"study_design_scores_gemma":[0.001028974,0.00001974188,0.945515,0.0002749769,0.000122106,1.316025e-7,0.02680061,0.001190324,0.00001686459,0.02293705,0.001755188,0.0003390166],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.979457,0.0004559931,0.007819536,0.001447585,0.0005065984,0.002063226,0.00001113582,0.00008215051,0.008156798],"genre_scores_gemma":[0.9884803,0.0002652574,0.009081408,0.0001830669,0.0001407781,0.0001532817,0.0001802492,0.00002130501,0.001494407],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04464496,"threshold_uncertainty_score":0.9995598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5525181649584399,"score_gpt":0.4634122860090244,"score_spread":0.08910587894941546,"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."}}