{"id":"W3211945175","doi":"10.1145/3488269","title":"Towards a Consistent Interpretation of AIOps Models","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Huawei Technologies (Canada); Queen's University","funders":"","keywords":"Consistency (knowledge bases); Interpretation (philosophy); Computer science; Machine learning; Randomness; Consistency model; Artificial intelligence; Hyperparameter; Data mining; Econometrics; Statistics; Algorithm; Mathematics; Correctness","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":[0.04073243,0.001987373,0.001829854,0.005091633,0.00147857,0.01025173,0.00484883,0.002548229,0.001527709],"category_scores_gemma":[0.2084255,0.001516267,0.00196705,0.00340098,0.003107285,0.00972414,0.005056063,0.007099884,0.0007668622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003161945,"about_ca_system_score_gemma":0.005371824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003434569,"about_ca_topic_score_gemma":0.004668813,"domain_scores_codex":[0.9547961,0.0279416,0.003401029,0.00512262,0.007862473,0.0008760442],"domain_scores_gemma":[0.8314191,0.102399,0.0123274,0.02434178,0.02777378,0.001739022],"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":[0.0007277566,0.0005022928,0.07407919,0.001245887,0.0009865839,0.001255582,0.01084408,0.4097506,0.005511052,0.2671649,0.02445081,0.2034811],"study_design_scores_gemma":[0.0000694304,0.000088206,0.002926302,0.0002950565,0.00009338446,0.0001236449,0.001111747,0.6721588,0.0020015,0.3135206,0.007536311,0.00007494169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0537554,0.0004932075,0.9346203,0.004406387,0.000177775,0.0002792185,0.001357857,0.001392192,0.003517646],"genre_scores_gemma":[0.5044914,0.0003271323,0.4886094,0.00114185,0.0001736893,0.0005792277,0.003277032,0.0006671118,0.0007330743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04073243,"threshold_uncertainty_score":0.2154163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09577591198243182,"score_gpt":0.316722677026575,"score_spread":0.2209467650441432,"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."}}