{"id":"W4411449762","doi":"10.1145/3729346","title":"CAShift: Benchmarking Log-Based Cloud Attack Detection under Normality Shift","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":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Cloud computing; Computer science; Normality; Benchmarking; Data mining; Construct (python library); Paradigm shift; Anomaly detection; Statistics; Mathematics; Operating system","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":[0.0006999117,0.0002678172,0.000304255,0.000200715,0.0001934546,0.0001057574,0.002578036,0.0001773468,0.000003673044],"category_scores_gemma":[0.001543404,0.0002016656,0.0002081763,0.001062542,0.00005934306,0.0003690622,0.0008301795,0.0003769938,0.00000884695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002033572,"about_ca_system_score_gemma":0.00008664463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003249786,"about_ca_topic_score_gemma":0.000004345973,"domain_scores_codex":[0.9982846,0.00001081775,0.0004292343,0.0004768244,0.0004270341,0.000371476],"domain_scores_gemma":[0.9982176,0.0002886547,0.0001956004,0.001014296,0.0002171382,0.0000666889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003157552,0.0008555728,0.7367319,0.008007373,0.0005128801,0.000004294453,0.002190741,0.1640495,0.004330539,0.03520628,0.00990606,0.03788913],"study_design_scores_gemma":[0.001415369,0.0003619788,0.774841,0.001582493,0.00008001058,0.00001358303,0.00004093252,0.08240513,0.1288451,0.004439272,0.004960058,0.001015092],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7640775,0.00008985312,0.2310026,0.0009985976,0.002594907,0.0004010533,0.000003702004,0.0007090922,0.000122668],"genre_scores_gemma":[0.9816473,0.000002404783,0.01780017,0.0003209391,0.0001357898,0.00004191617,5.229709e-7,0.00001576156,0.00003519153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2175698,"threshold_uncertainty_score":0.8223686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01056494758060279,"score_gpt":0.232949269598238,"score_spread":0.2223843220176352,"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."}}