{"id":"W4399871949","doi":"10.1007/s10664-024-10501-4","title":"Systematic Evaluation of Deep Learning Models for Log-based Failure Prediction","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"HORIZON EUROPE Framework Programme; Canada Research Chairs; Natural Sciences and Engineering Research Council of Canada; European Commission; Science Foundation Ireland; Université du Luxembourg","keywords":"Computer science; Machine learning; Artificial intelligence; Artificial neural network; Algorithm; Convolutional neural network; Deep learning; Encoder; Predictive modelling; Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001802319,0.0001583008,0.0002844926,0.0001732142,0.00006605384,0.00008610819,0.0002689055,0.0001300262,0.000004740838],"category_scores_gemma":[0.001141236,0.0001295631,0.0001665705,0.0004904278,0.0000122286,0.0004824531,0.00004438586,0.0001755511,0.000008132311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002028684,"about_ca_system_score_gemma":0.0001039763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002378913,"about_ca_topic_score_gemma":6.923145e-7,"domain_scores_codex":[0.9982778,0.0000859886,0.000468572,0.0003496885,0.0005889641,0.0002289537],"domain_scores_gemma":[0.9984323,0.0008396786,0.00006552543,0.0003170718,0.0002786901,0.00006675566],"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":[0.000001907929,0.00001541261,0.001289582,0.01267336,0.00003877226,6.219881e-7,0.0004280924,0.9831648,0.00003172829,0.0001417765,0.00005932459,0.002154548],"study_design_scores_gemma":[0.0002034737,0.00007822627,0.0005767031,0.001976764,0.00006426674,0.000005096892,0.00001233481,0.996222,0.0002419204,0.0003859075,0.0001065104,0.0001267508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02206518,0.001525577,0.9737974,0.00007844345,0.0007155329,0.0007536022,0.00000370319,0.001054915,0.000005572862],"genre_scores_gemma":[0.9552712,0.000001966541,0.04425906,0.00001185353,0.00009265574,0.0003229951,0.00001078292,0.00002032209,0.000009108267],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9332061,"threshold_uncertainty_score":0.5283428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03017146570369021,"score_gpt":0.2758273760452596,"score_spread":0.2456559103415694,"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."}}