{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1401171,0.0006671895,0.001175684,0.006753013,0.001598862,0.004496042,0.001762388,0.0009452548,0.00241467],"category_scores_gemma":[0.2671724,0.0004583013,0.0008152241,0.005588285,0.0105876,0.005068316,0.003366785,0.001921468,0.0003441873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003850225,"about_ca_system_score_gemma":0.002745606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003583366,"about_ca_topic_score_gemma":0.004682745,"domain_scores_codex":[0.7922568,0.1674148,0.007081265,0.005336036,0.02670807,0.001202981],"domain_scores_gemma":[0.7177724,0.2045802,0.02413479,0.0179447,0.03391995,0.001647997],"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":[0.0004294066,0.0001703782,0.06448479,0.003143228,0.0005199414,0.00008605641,0.0269605,0.00174795,0.001444741,0.1535058,0.006553879,0.7409534],"study_design_scores_gemma":[0.0003163829,0.00121984,0.4202022,0.01141397,0.0005303207,0.000719382,0.02188343,0.01172797,0.003670554,0.4224545,0.1054288,0.0004326624],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3704813,0.1138406,0.3408853,0.03184494,0.002296242,0.001451442,0.000642919,0.0004619737,0.1380954],"genre_scores_gemma":[0.9209146,0.008115455,0.06606627,0.00166027,0.000516959,0.0009404285,0.0001086318,0.0001057389,0.001571506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1401171,"threshold_uncertainty_score":0.7410188,"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."}}