{"id":"W4389685461","doi":"10.1007/s10664-023-10409-5","title":"Detection and evaluation of bias-inducing features in machine learning","year":2023,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Consortium de Recherche et d’innovation en Aérospatiale au Québec","keywords":"Computer science; Machine learning; Identification (biology); Context (archaeology); Artificial intelligence; Harm; Feature (linguistics); Outcome (game theory); Data mining; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.007013545,0.0006388181,0.0008907859,0.002285584,0.0005458346,0.001818217,0.0009391006,0.001520806,0.0007912155],"category_scores_gemma":[0.04561867,0.0002792221,0.0005022235,0.001086174,0.0006648891,0.001454175,0.001323385,0.00122203,0.0003292823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007478605,"about_ca_system_score_gemma":0.001201412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001322734,"about_ca_topic_score_gemma":0.001793225,"domain_scores_codex":[0.996981,0.001060063,0.0002494391,0.0004670523,0.001013933,0.0002285514],"domain_scores_gemma":[0.9551312,0.03229308,0.003384037,0.00351224,0.004894659,0.0007847741],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002679861,0.0008604527,0.1793462,0.0007360547,0.0004328728,0.000319684,0.000278861,0.0659586,0.04713005,0.009052393,0.004544269,0.6886607],"study_design_scores_gemma":[0.0001644962,0.0004709359,0.02734446,0.00009220833,0.0001821582,0.0002572579,0.00009862026,0.9121817,0.04679354,0.01115065,0.001225743,0.00003830316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7207711,0.002116534,0.2713148,0.0004731644,0.0001168051,0.0001665032,0.0006026205,0.002848166,0.00159024],"genre_scores_gemma":[0.9522358,0.0001683373,0.04624134,0.0000591415,0.00004062802,0.00004111858,0.0007300905,0.0001497857,0.0003337729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9929864,"threshold_uncertainty_score":0.03709161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06541519331576667,"score_gpt":0.314828704639924,"score_spread":0.2494135113241573,"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."}}