{"id":"W4413024567","doi":"10.1111/coin.70113","title":"Taming the Triangle: On the Interplays Between Fairness, Interpretability, and Privacy in Machine Learning","year":2025,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal; Polytechnique Montréal","funders":"Canada Research Chairs; Centre International de Mathématiques et Informatique de Toulouse; Agence Nationale de la Recherche; Polytechnique Montréal","keywords":"Interpretability; Computer science; Artificial intelligence; Machine learning; Natural language processing","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":[],"consensus_categories":[],"category_scores_codex":[0.02771385,0.001043992,0.001529794,0.001830532,0.002008791,0.008329655,0.002762631,0.003945739,0.004071007],"category_scores_gemma":[0.09137078,0.0009337357,0.001167693,0.001759661,0.01718143,0.01505696,0.008361683,0.008586407,0.0006168622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002337005,"about_ca_system_score_gemma":0.001794564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005280167,"about_ca_topic_score_gemma":0.0003474748,"domain_scores_codex":[0.9610021,0.0281455,0.001189861,0.002998069,0.005292454,0.001372059],"domain_scores_gemma":[0.8214391,0.1531381,0.005958391,0.01425843,0.003839476,0.001366452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009398151,0.00004027222,0.0009232688,0.0001874456,0.00006373283,0.0001351707,0.0005032732,0.01188748,0.0005775415,0.9630359,0.00125333,0.02129865],"study_design_scores_gemma":[0.00001547748,0.00006271986,0.0003512596,0.0002145184,0.00004085083,0.0001347787,0.0001563318,0.04379688,0.0009503471,0.9501873,0.004053844,0.00003563457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04899798,0.009887285,0.8919513,0.02362243,0.0003407492,0.0001075054,0.00009292912,0.0002033194,0.02479641],"genre_scores_gemma":[0.9341117,0.00447929,0.05617416,0.002353994,0.0007390364,0.0001691124,0.00004663745,0.0001152406,0.001810784],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02771385,"threshold_uncertainty_score":0.1465666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02465387779662896,"score_gpt":0.303107553909016,"score_spread":0.278453676112387,"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."}}