{"id":"W4409405452","doi":"10.1007/s10664-025-10656-8","title":"Logging requirement for continuous auditing of responsible machine learning-based applications","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Audit; Logging; Computer science; Business; Accounting; Forestry; 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":[0.01485816,0.0008848664,0.001501967,0.00152832,0.001668409,0.004363629,0.003542537,0.00323331,0.007536263],"category_scores_gemma":[0.1577686,0.001079541,0.0009190487,0.0007676292,0.002810092,0.007769313,0.005125735,0.005919969,0.002968346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001277999,"about_ca_system_score_gemma":0.006088249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00110203,"about_ca_topic_score_gemma":0.0007990299,"domain_scores_codex":[0.9766692,0.004859299,0.002965315,0.002927978,0.01009707,0.002481053],"domain_scores_gemma":[0.7311523,0.09442358,0.01905126,0.1234628,0.02673141,0.005178599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005407839,0.002075855,0.06169327,0.001458525,0.000305903,0.004536116,0.001883871,0.1121319,0.1404928,0.2331622,0.0285726,0.4082792],"study_design_scores_gemma":[0.0002157181,0.0007173778,0.01257195,0.000370202,0.0001454084,0.002628132,0.00047983,0.7283096,0.09796417,0.1422495,0.01417418,0.0001738928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1899088,0.00039672,0.7685542,0.003924226,0.0006581001,0.0007427236,0.0006833787,0.02518581,0.009946037],"genre_scores_gemma":[0.9582897,0.00006778966,0.03779342,0.000508827,0.0001205363,0.0001926468,0.0002861895,0.0005954651,0.002145411],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01485816,"threshold_uncertainty_score":0.07857835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01588830281863251,"score_gpt":0.2931712096872442,"score_spread":0.2772829068686117,"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."}}