{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003328699,0.00009400652,0.0001954267,0.0001345042,0.00003301829,0.00001678221,0.0002544249,0.00008276553,0.000005461161],"category_scores_gemma":[0.0006452624,0.00009892938,0.0000511873,0.0002305189,0.00003099618,0.0001897437,0.0000211632,0.0001429158,9.713511e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002263406,"about_ca_system_score_gemma":0.00005656571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008072182,"about_ca_topic_score_gemma":0.000001292903,"domain_scores_codex":[0.9991991,0.0001353461,0.0002040888,0.0002565063,0.00008782052,0.0001171214],"domain_scores_gemma":[0.998484,0.0007234393,0.0000472393,0.000580326,0.0001203313,0.00004464622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002277015,0.00009831651,0.00001472283,0.0001388383,0.0001035873,0.00001099079,0.001544869,0.05039012,0.01718625,0.05618871,0.00003616509,0.8742647],"study_design_scores_gemma":[0.0006179137,0.000273574,0.001131143,0.0001715857,0.00006722621,0.0003302792,0.0001368029,0.452937,0.5096563,0.03252737,0.001679434,0.000471359],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001076777,0.0001701084,0.9978276,0.000282966,0.0002369947,0.00005668308,0.00001491618,0.00031374,0.00002015063],"genre_scores_gemma":[0.2043355,0.0001101599,0.7953929,0.00009009073,0.000004399479,0.0000264148,0.000004259631,0.000006581861,0.00002970224],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8737933,"threshold_uncertainty_score":0.4034223,"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."}}