{"id":"W2951029771","doi":"10.22148/16.041","title":"Data Set Failures and Intersectional Data","year":2019,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Open source software; Software; Computer science; Set (abstract data type); Open source; White (mutation); Data science; Sociology; World Wide Web; Internet privacy; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1744696,0.001281622,0.002283369,0.009971747,0.008988223,0.008640832,0.00803201,0.003438867,0.01736408],"category_scores_gemma":[0.5107896,0.001874375,0.001905409,0.02186016,0.01054561,0.01130946,0.01485719,0.008218706,0.003722807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006477652,"about_ca_system_score_gemma":0.007908081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01555071,"about_ca_topic_score_gemma":0.01434773,"domain_scores_codex":[0.7377634,0.1349641,0.02733034,0.04066691,0.05150905,0.007766152],"domain_scores_gemma":[0.4167375,0.3786443,0.03281341,0.1168327,0.04994088,0.005031137],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002072419,0.0005030361,0.446925,0.002645531,0.001318359,0.002088372,0.02778051,0.009116187,0.0009050333,0.2634651,0.1446697,0.09851081],"study_design_scores_gemma":[0.0003564221,0.0003832073,0.09095268,0.002899216,0.0006650858,0.003489734,0.03029392,0.03035873,0.004982065,0.3836,0.4516683,0.0003506244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3643236,0.005600951,0.3606781,0.04613405,0.004498779,0.004103406,0.133575,0.005113735,0.07597243],"genre_scores_gemma":[0.7517263,0.0004588302,0.1369842,0.005233146,0.0005412304,0.007237769,0.09007996,0.001715226,0.00602324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8255304,"threshold_uncertainty_score":0.9226947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2246225217285764,"score_gpt":0.4503909631259252,"score_spread":0.2257684413973489,"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."}}