{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00128023,0.0001090522,0.0002395892,0.0001055903,0.0001248292,0.0000106598,0.001444897,0.00006044004,0.000004706066],"category_scores_gemma":[0.002157301,0.00006819873,0.0000615481,0.0005192804,0.00006559415,0.0001742668,0.0001577104,0.0002617435,1.71239e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001496826,"about_ca_system_score_gemma":0.00008928108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006921813,"about_ca_topic_score_gemma":0.000008743124,"domain_scores_codex":[0.9986985,0.0004303037,0.0002841391,0.0002864558,0.0001499656,0.0001506352],"domain_scores_gemma":[0.992331,0.004918979,0.00009269165,0.002529755,0.00009073278,0.00003686042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000121569,0.003835294,0.03593044,0.0001126409,0.0008398703,0.000009968004,0.0122431,0.2329169,0.02280841,0.001602079,0.0003009905,0.6892787],"study_design_scores_gemma":[0.001379069,0.007200676,0.5400544,0.0007024916,0.000340774,0.0002914001,0.001870408,0.3412456,0.1047537,0.00126071,0.0002055807,0.0006951144],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4734015,0.000017387,0.5263311,0.00004940678,0.00005294392,0.00006206836,0.00004313125,0.00004154245,9.623911e-7],"genre_scores_gemma":[0.5791912,0.00001886032,0.4207627,0.000007676166,0.000004333511,0.000006319928,0.000002085768,0.000004884895,0.000001899547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6885836,"threshold_uncertainty_score":0.2781064,"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."}}