{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1727708,0.0006769874,0.001315962,0.002051664,0.002564737,0.002171325,0.002672662,0.001579982,0.001911248],"category_scores_gemma":[0.4614524,0.0005482759,0.001210471,0.001626809,0.005541846,0.003366301,0.003368671,0.002450354,0.0003567871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001409557,"about_ca_system_score_gemma":0.001043832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002740706,"about_ca_topic_score_gemma":0.004698959,"domain_scores_codex":[0.8168706,0.1099769,0.01362621,0.01980124,0.03801091,0.001714056],"domain_scores_gemma":[0.5368019,0.3456261,0.04002145,0.05351651,0.02140386,0.002630187],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003251814,0.001034912,0.6064402,0.001541406,0.002785458,0.001246998,0.06126074,0.00100311,0.00372842,0.0174755,0.01572591,0.2845055],"study_design_scores_gemma":[0.0008618009,0.00439847,0.7889156,0.002090271,0.001818896,0.002548916,0.04696078,0.01207388,0.01283147,0.08237509,0.04470991,0.0004149805],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8644946,0.00428108,0.1095435,0.008309213,0.001688483,0.001966727,0.0005251581,0.0003746597,0.008816737],"genre_scores_gemma":[0.9750271,0.0001638977,0.01928601,0.003330698,0.0002973243,0.001226161,0.000176032,0.00007654812,0.0004161916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8272291,"threshold_uncertainty_score":0.9137105,"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."}}