{"id":"W4254642198","doi":"10.31235/osf.io/j2tw9","title":"Scaling Down Inequality: Rating Scales, Gender Bias, and the Architecture of Evaluation","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Management and Organizational Studies","field":"Business, Management and Accounting","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Inequality; Scale (ratio); Gender bias; Gender inequality; Rating scale; Psychology; Social psychology; Applied psychology; Developmental psychology; Mathematics; Geography","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":[0.1330552,0.0007362657,0.0009964914,0.004185113,0.002165364,0.00503038,0.001544389,0.0009420076,0.003648214],"category_scores_gemma":[0.3533782,0.000606223,0.000680919,0.003261769,0.009460402,0.006467928,0.004129699,0.001923678,0.0005055876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003232689,"about_ca_system_score_gemma":0.002197648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002420768,"about_ca_topic_score_gemma":0.002499114,"domain_scores_codex":[0.7999218,0.1593216,0.006484138,0.0071433,0.02552198,0.001607127],"domain_scores_gemma":[0.6388876,0.253536,0.02994793,0.04075918,0.03427491,0.002594382],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001241231,0.0004488772,0.1522047,0.001179383,0.0004319005,0.0001477064,0.05394729,0.003738331,0.00788157,0.1940923,0.004887964,0.5797987],"study_design_scores_gemma":[0.0004621338,0.001735831,0.410303,0.002245959,0.0003092012,0.0004746584,0.02069692,0.03966827,0.01080348,0.4754697,0.03737709,0.0004537337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5097095,0.003715187,0.3947272,0.009807247,0.0005052321,0.0009331004,0.0002971421,0.0005522477,0.07975312],"genre_scores_gemma":[0.9323083,0.0002832101,0.06527461,0.0004574178,0.0001136006,0.0005114011,0.00005765483,0.00009728321,0.0008965022],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8669448,"threshold_uncertainty_score":0.7036718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05755389007696215,"score_gpt":0.2674084499638921,"score_spread":0.2098545598869299,"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."}}