{"id":"W3184231327","doi":"10.1145/3447876","title":"An Empirical Study of the Impact of Data Splitting Decisions on the Performance of AIOps Solutions","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; École de Technologie Supérieure; Polytechnique Montréal; Queen's University","funders":"","keywords":"Computer science; Concept drift; Leakage (economics); Cloud computing; Data mining; Context (archaeology); Data science; TRACE (psycholinguistics); Data stream mining","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":[0.01195915,0.001043189,0.0005959041,0.001264265,0.00108174,0.001944468,0.001463505,0.001351103,0.001306197],"category_scores_gemma":[0.07403709,0.0003792275,0.0005870179,0.001885981,0.0009079865,0.005070276,0.001543581,0.003126967,0.0005241428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001227524,"about_ca_system_score_gemma":0.001260639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002438862,"about_ca_topic_score_gemma":0.002173227,"domain_scores_codex":[0.9910377,0.00337769,0.0009790008,0.001299994,0.002311809,0.0009937854],"domain_scores_gemma":[0.9217473,0.05324896,0.00613886,0.007845934,0.007683454,0.003335639],"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":[0.00422508,0.006101967,0.2220129,0.001720294,0.0007717688,0.0004745846,0.001969507,0.3875677,0.02044897,0.00507567,0.01705459,0.332577],"study_design_scores_gemma":[0.0003206305,0.00606828,0.06746844,0.0002240111,0.0002660801,0.000501632,0.003274391,0.8890836,0.01649445,0.006332919,0.009853081,0.0001123726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877616,0.0009135035,0.007275653,0.0006555979,0.0001009153,0.0002189416,0.0006890076,0.0004693679,0.001915496],"genre_scores_gemma":[0.9855802,0.000282533,0.01168332,0.0001667632,0.00004167565,0.0001377883,0.001600214,0.00005782422,0.0004496844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01195915,"threshold_uncertainty_score":0.06324679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2584045887855763,"score_gpt":0.416978530640578,"score_spread":0.1585739418550018,"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."}}