{"id":"W2921085129","doi":"10.1177/0003122419833601","title":"Scaling Down Inequality: Rating Scales, Gender Bias, and the Architecture of Evaluation","year":2019,"lang":"en","type":"article","venue":"American Sociological Review","topic":"Gender Diversity and Inequality","field":"Social Sciences","cited_by":202,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Inequality; Scale (ratio); Rating scale; Psychology; Gender bias; Gender inequality; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01079445,0.00009618433,0.0004918287,0.00001319647,0.0002634627,0.00001721804,0.0001866117,0.00005863808,0.0003447924],"category_scores_gemma":[0.004050186,0.00005485775,0.0001511377,0.0002629881,0.00185225,0.00005223933,0.0001026085,0.0002180724,0.00002113666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004145786,"about_ca_system_score_gemma":0.00008763678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009193959,"about_ca_topic_score_gemma":0.00002417961,"domain_scores_codex":[0.9942163,0.004517986,0.0003197113,0.0002305871,0.0005070507,0.0002083455],"domain_scores_gemma":[0.9976525,0.001581933,0.0003734811,0.0001836855,0.0001425173,0.0000658585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006758379,0.00008741033,0.08597258,0.001218306,0.0001412018,8.350966e-7,0.03232438,0.00003671132,0.00007446246,0.1357495,0.0009545038,0.7433725],"study_design_scores_gemma":[0.006015236,0.0007676771,0.3956583,0.003293127,0.001657926,0.00001058368,0.2026048,0.0007655802,0.00003214465,0.2123304,0.1747185,0.002145636],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.919769,0.05172951,0.0004960177,0.01033181,0.00008358051,0.001420572,0.00001017683,0.00004056574,0.01611873],"genre_scores_gemma":[0.9658884,0.02939971,0.0003919803,0.004220418,0.00005684498,0.00001325476,0.000006993002,0.00000249465,0.00001983474],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7412269,"threshold_uncertainty_score":0.6824692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2146327434493752,"score_gpt":0.3896147971780902,"score_spread":0.1749820537287149,"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."}}