{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006548486,0.0001885336,0.0003092406,0.0002841431,0.0001993529,0.00005493798,0.0006073925,0.00008834333,0.000007332347],"category_scores_gemma":[0.002605817,0.0002018151,0.0001273988,0.0006933968,0.00002896698,0.0001303685,0.0002494657,0.0003341133,0.000002948239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001292658,"about_ca_system_score_gemma":0.0001552247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001065048,"about_ca_topic_score_gemma":0.000001119517,"domain_scores_codex":[0.9985346,0.00005927759,0.0004200973,0.0004074744,0.000217124,0.000361428],"domain_scores_gemma":[0.997465,0.001800084,0.0001566373,0.0003951095,0.0001139884,0.00006925536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001870914,0.00004280972,0.01965893,0.0002372566,0.00003439525,0.000002488217,0.0001001375,0.9645544,0.0005482498,0.005320205,0.0001690839,0.009313358],"study_design_scores_gemma":[0.0006348061,0.00007424141,0.002267707,0.0001454001,0.00002093478,0.000001288812,0.000009818369,0.9405016,0.002519875,0.0005765163,0.05301087,0.0002369244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001710132,0.0002110375,0.9958072,0.0008127785,0.0002207186,0.0004121232,0.000003911425,0.0007330793,0.00008904434],"genre_scores_gemma":[0.5337496,0.00000152582,0.4656082,0.0001641894,0.00006774092,0.0001711204,0.00001289592,0.00002264249,0.0002021225],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5320394,"threshold_uncertainty_score":0.8229781,"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."}}