{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03456973,0.0009616722,0.001065181,0.00143881,0.0008819599,0.002670258,0.001293212,0.001425698,0.001220725],"category_scores_gemma":[0.2280311,0.0006332552,0.001068346,0.001670799,0.001258517,0.005907176,0.001810634,0.003254536,0.0002912562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001522674,"about_ca_system_score_gemma":0.002685632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005098096,"about_ca_topic_score_gemma":0.004385225,"domain_scores_codex":[0.9899169,0.004693016,0.0009642222,0.001488892,0.002301248,0.0006357379],"domain_scores_gemma":[0.7289177,0.2383585,0.008317854,0.01407384,0.009015996,0.001316197],"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":[0.002305445,0.0005558642,0.234381,0.000290809,0.0005337649,0.0004557923,0.0004369201,0.5917906,0.003601316,0.009135723,0.002662647,0.1538501],"study_design_scores_gemma":[0.00001981174,0.0002202964,0.007744998,0.00003590944,0.0001124292,0.0002058138,0.00006198085,0.9827079,0.002111096,0.006445262,0.0003169431,0.00001749681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8076637,0.003005336,0.182173,0.002719382,0.0003609068,0.0001066928,0.001318841,0.0011786,0.001473624],"genre_scores_gemma":[0.987201,0.0003248101,0.01128572,0.0001598345,0.00005877213,0.00002581806,0.0004268471,0.0000646202,0.0004525702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03456973,"threshold_uncertainty_score":0.1828244,"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."}}