{"id":"W4324299382","doi":"10.48550/arxiv.2303.07230","title":"Systematic Evaluation of Deep Learning Models for Log-based Failure Prediction","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission; Science Foundation Ireland; Université du Luxembourg","keywords":"Computer science; Artificial intelligence; Deep learning; Machine learning; Modular design; Encoder; Convolutional neural network; Embedding; Artificial neural network; Dependability; Metric (unit); Data mining; Autoencoder","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005652343,0.002433673,0.0008561009,0.001423218,0.0003863169,0.0009323246,0.001803355,0.001290948,0.001230379],"category_scores_gemma":[0.01495437,0.0005517579,0.001075098,0.0009203885,0.0005901718,0.002162735,0.001169754,0.001739995,0.0005528743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001617999,"about_ca_system_score_gemma":0.001238693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01085403,"about_ca_topic_score_gemma":0.01297326,"domain_scores_codex":[0.9976133,0.001036877,0.0002545532,0.0005289143,0.000389581,0.0001768132],"domain_scores_gemma":[0.9916657,0.005190582,0.0004436762,0.001104982,0.001385518,0.0002095843],"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":[0.001557975,0.001038083,0.02481767,0.001169116,0.0007328939,0.0001585365,0.0001041795,0.758017,0.005334004,0.001363747,0.009323562,0.1963833],"study_design_scores_gemma":[0.00007079531,0.0005030549,0.004051032,0.00007961545,0.00009655821,0.00004585831,0.00004620061,0.9880356,0.005450862,0.0006143227,0.0009845744,0.00002153455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8852309,0.007363238,0.08396409,0.001546802,0.0004686538,0.0005410357,0.009247371,0.006491383,0.005146436],"genre_scores_gemma":[0.9366127,0.001110563,0.0438953,0.0002339869,0.00006042544,0.0002912948,0.01645442,0.0001740487,0.001167243],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01085403,"threshold_uncertainty_score":0.0298928,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1194605287504361,"score_gpt":0.2168916450397203,"score_spread":0.0974311162892842,"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."}}