{"id":"W3011013547","doi":"10.1109/ccwc47524.2020.9031232","title":"AIOPS Prediction for Hard Drive Failures Based on Stacking Ensemble Model","year":2020,"lang":"en","type":"article","venue":"2020 10th Annual Computing and Communication Workshop and Conference (CCWC)","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kensington Health","funders":"","keywords":"Computer science; Stacking; Feature extraction; Artificial intelligence; Process (computing); Ensemble forecasting; Ensemble learning; Data mining; Machine learning; Raw data; Filter (signal processing); Feature (linguistics); Pattern recognition (psychology); Computer vision","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":[0.0002198223,0.0002267853,0.0002557898,0.00007028859,0.0005647864,0.0003285408,0.0009912065,0.0001267132,0.000001607441],"category_scores_gemma":[0.0003009528,0.0002251545,0.00004211632,0.0002885567,0.0001515156,0.0005252764,0.0007505841,0.0003919766,0.000002678241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000023415,"about_ca_system_score_gemma":0.00007965844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008105432,"about_ca_topic_score_gemma":0.000009938811,"domain_scores_codex":[0.9985508,0.00009531485,0.0002973908,0.0005757451,0.0001953715,0.0002853618],"domain_scores_gemma":[0.9981956,0.0004579715,0.0001864884,0.000792928,0.0002282523,0.0001386963],"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":[0.0001800443,0.0001161583,0.0006562785,0.000125897,0.00004984759,0.000004235624,0.009103418,0.09306861,0.0006792133,0.2124363,0.006381586,0.6771984],"study_design_scores_gemma":[0.0004913519,0.000187214,0.0001704082,0.0001231361,0.00001163466,0.000002308377,0.00204393,0.9885515,0.0002255162,0.006096951,0.001868306,0.0002277653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01002256,0.0003389057,0.9744095,0.01399026,0.00004074884,0.0003033051,0.00006710529,0.0005972388,0.0002303804],"genre_scores_gemma":[0.808998,0.0001583136,0.1894603,0.001242583,0.00002808726,0.00002295573,0.00005680019,0.00001111664,0.00002175836],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8954828,"threshold_uncertainty_score":0.9181534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04081647050436263,"score_gpt":0.2763858449968022,"score_spread":0.2355693744924396,"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."}}