{"id":"W4411450220","doi":"10.1145/3715779","title":"Protecting Privacy in Software Logs: What Should Be Anonymized?","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Identification (biology); Computer science; Information privacy; Personally identifiable information; Privacy policy; Information sensitivity; Data anonymization; Software; Privacy by Design; Data science; Identifier; Internet privacy; Computer security","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001064882,0.0003431202,0.0004687283,0.0003806002,0.0001555612,0.0002525007,0.004498183,0.0002241095,0.000003671033],"category_scores_gemma":[0.01234031,0.0002535658,0.0002000719,0.001694764,0.00005794855,0.001323094,0.002141835,0.0007307274,0.000005452261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002099344,"about_ca_system_score_gemma":0.0001111899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002485175,"about_ca_topic_score_gemma":0.000001120855,"domain_scores_codex":[0.9977186,0.00001536873,0.0006053094,0.0006332349,0.0005212837,0.0005061991],"domain_scores_gemma":[0.997616,0.0004984665,0.0002282051,0.001303582,0.0002845961,0.00006917786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000361378,0.001187356,0.7846048,0.0129149,0.0004063678,0.00001296082,0.01247989,0.01533841,0.006129023,0.01017256,0.01630945,0.1400829],"study_design_scores_gemma":[0.01190875,0.001388561,0.4190789,0.03502314,0.0001927352,0.0001495422,0.001881806,0.04590895,0.3806573,0.02860608,0.06967791,0.005526336],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9364184,0.0009953958,0.04877483,0.007182294,0.002774548,0.002032044,0.000004309474,0.001732503,0.00008571518],"genre_scores_gemma":[0.8398452,0.00007237424,0.158287,0.001069717,0.0001027707,0.0003164757,9.268008e-7,0.0000473094,0.0002581523],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3745283,"threshold_uncertainty_score":0.9999917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01804381769544553,"score_gpt":0.2513165258656156,"score_spread":0.2332727081701701,"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."}}