{"id":"W2164917791","doi":"10.1109/phm.2008.4711453","title":"Improving preciseness of time to failure predictions: Application to APU starter","year":2008,"lang":"en","type":"article","venue":"","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada; Astellas Pharma US","keywords":"Prognostics; Cluster analysis; Computer science; Component (thermodynamics); Aerospace; Support vector machine; Data mining; Machine learning; Reliability engineering; Artificial intelligence; Engineering","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":[0.000258317,0.00006989819,0.0001316168,0.0001798242,0.00009823369,0.0000348885,0.0005864522,0.00003949322,0.00009803131],"category_scores_gemma":[0.0001231853,0.00006002738,0.00005666026,0.0009588233,0.00002434913,0.0002495046,0.000242859,0.00005934653,0.0006639084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004163639,"about_ca_system_score_gemma":0.00007404217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001655852,"about_ca_topic_score_gemma":0.00002094979,"domain_scores_codex":[0.9988452,0.00003940603,0.000208953,0.0003481139,0.0003792763,0.000179101],"domain_scores_gemma":[0.9988229,0.0001093621,0.00002981324,0.0006447336,0.0002462425,0.0001469244],"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":[0.00007173507,0.001015723,0.0164294,0.0001855738,0.0001472462,0.000007923401,0.004671738,0.03769023,0.1529287,0.002912411,0.0423173,0.741622],"study_design_scores_gemma":[0.0004545829,0.0005566187,0.01677478,0.00004415103,0.00001757624,0.00002260633,0.0000893945,0.888513,0.05537954,0.0008969996,0.03671017,0.0005405785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02854601,0.000007185368,0.9690654,0.001507022,0.00001310364,0.0003200519,0.000002878577,0.0001304001,0.0004079923],"genre_scores_gemma":[0.8599722,0.000003824719,0.1365182,0.0002490201,0.00005721187,0.0001594269,0.000003964375,0.000007579184,0.003028533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8508227,"threshold_uncertainty_score":0.8533421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009138767481495032,"score_gpt":0.2408145764655157,"score_spread":0.2316758089840207,"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."}}