{"id":"W3122321999","doi":"10.14293/s2199-1006.1.sor.2021.0001.v1","title":"Small samples, unreasonable generalizations, and outliers: Gender bias in student evaluation of teaching or three unhappy students?","year":2021,"lang":"en","type":"preprint","venue":"ScienceOpen Research","topic":"Communication in Education and Healthcare","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Royal University","funders":"","keywords":"Psychology; Outlier; Set (abstract data type); Gender bias; 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":[0.1431424,0.000612482,0.00108548,0.0016962,0.002706965,0.002033639,0.002490351,0.001730695,0.001803017],"category_scores_gemma":[0.423132,0.0004526997,0.001062733,0.001328067,0.005043399,0.002874166,0.002883472,0.00224453,0.0003276408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001541668,"about_ca_system_score_gemma":0.001152565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00337336,"about_ca_topic_score_gemma":0.005565896,"domain_scores_codex":[0.8381607,0.09449445,0.01084976,0.0186943,0.03626423,0.001536606],"domain_scores_gemma":[0.6121839,0.2837971,0.03585472,0.04625473,0.01938408,0.00252547],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002866118,0.00101449,0.6250463,0.001012924,0.002078569,0.001222426,0.05906045,0.000998372,0.003549241,0.01415077,0.01608164,0.2729187],"study_design_scores_gemma":[0.0007001326,0.00388311,0.8079324,0.001696058,0.001402153,0.002538688,0.04281685,0.01443231,0.0118941,0.07571639,0.0366128,0.0003749166],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8750693,0.003416394,0.1022697,0.008889351,0.001428642,0.001409608,0.0004566597,0.0003461259,0.006714294],"genre_scores_gemma":[0.9773842,0.000127467,0.01754145,0.00323563,0.0003006819,0.0008513456,0.0001501095,0.00006514681,0.0003439249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8568577,"threshold_uncertainty_score":0.7570183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8522916635758395,"score_gpt":0.6483096562453999,"score_spread":0.2039820073304396,"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."}}