{"id":"W4400988474","doi":"10.1007/s10664-024-10518-9","title":"The impact of concept drift and data leakage on log level prediction models","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Queen's University","funders":"","keywords":"Interpretability; Debugging; Computer science; Context (archaeology); Statement (logic); Machine learning; Data mining; Data science; Deep learning; Artificial intelligence; Programming language","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":[0.0002664668,0.0001316955,0.0001213203,0.00006718607,0.00005239028,0.0001759681,0.000932861,0.00005978713,0.000001676838],"category_scores_gemma":[0.0003185421,0.00008797411,0.00003927817,0.0002436137,0.00004070583,0.0006184513,0.000649567,0.0002091613,0.000002045557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004984815,"about_ca_system_score_gemma":0.00004788441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003354401,"about_ca_topic_score_gemma":6.484922e-7,"domain_scores_codex":[0.9990585,0.00001792869,0.0001760122,0.0003639049,0.0001894172,0.0001942612],"domain_scores_gemma":[0.9983782,0.0006335396,0.00002280385,0.0008789687,0.00001958684,0.00006696616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002672432,0.0001696118,0.007807621,0.0002169083,0.0004730168,0.0001213205,0.003490454,0.1811513,0.0007238744,0.02321766,0.2648278,0.5177736],"study_design_scores_gemma":[0.00005291123,0.0001562091,0.006502839,0.0001178422,0.000005637132,0.00001604158,0.00000237627,0.9892226,0.0005113566,0.001045895,0.002255382,0.0001108734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01084577,0.0005636,0.9869044,0.0001431824,0.0001704684,0.00008760177,0.0002889703,0.0009644349,0.00003151057],"genre_scores_gemma":[0.9320875,0.00003446692,0.06768616,0.0000167259,0.00007246355,0.00000836233,0.00004595282,0.00001883565,0.00002955343],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9212417,"threshold_uncertainty_score":0.358748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09240412971559399,"score_gpt":0.3413998335328612,"score_spread":0.2489957038172673,"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."}}