{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001493521,0.00006343079,0.0001668074,0.00004049711,0.0002001803,0.0003254639,0.0008985309,0.00008517875,0.0001472133],"category_scores_gemma":[0.001124614,0.0000435012,0.00003685928,0.0001207714,0.0001569872,0.002000691,0.0002998422,0.0003341513,0.00001106893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003778985,"about_ca_system_score_gemma":0.0002053378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006809602,"about_ca_topic_score_gemma":0.00258123,"domain_scores_codex":[0.9989295,0.00008321556,0.0002410037,0.0001166257,0.0004882917,0.0001413869],"domain_scores_gemma":[0.9987435,0.0001538756,0.0002454949,0.0002540917,0.0004615548,0.0001415257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001949372,0.0002295062,0.0419037,0.000104202,0.001508915,0.00008933613,0.07526557,0.000193249,0.001142087,0.1420313,0.7274227,0.009914492],"study_design_scores_gemma":[0.000384679,0.0001183789,0.002943658,0.00007175843,0.000125996,0.00003395121,0.05070001,0.001261649,0.000006107804,0.006587523,0.9375955,0.0001707777],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8506387,0.000918973,0.0001383464,0.124229,0.001931573,0.0001566848,0.0004221368,0.0000210955,0.0215435],"genre_scores_gemma":[0.9954866,0.0008296716,0.0005909184,0.0004673208,0.0008576536,2.384905e-8,0.00003972444,0.000003728343,0.00172441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2101728,"threshold_uncertainty_score":0.3138456,"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."}}