{"id":"W4413906135","doi":"10.47191/etj/v10i08.46","title":"Deploying AI-Augmented Infrastructure Observability Pipelines for Predictive Fault Detection Using Logs, Metrics, and Traces","year":2025,"lang":"en","type":"article","venue":"Engineering and Technology Journal","topic":"Power Systems Fault Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"JDA Software (Canada); Glycemic Index Laboratories","funders":"","keywords":"Observability; Pipeline transport; Fault (geology); Computer science; Fault detection and isolation; Data mining; Real-time computing; Petroleum engineering; Engineering; Geology; Artificial intelligence; Seismology; Mathematics","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":[0.0002509895,0.0001918501,0.0002428822,0.0008755039,0.0001813199,0.00006627254,0.00008386852,0.0003213773,5.969118e-7],"category_scores_gemma":[0.0003694308,0.0001921916,0.00003562152,0.0006604388,0.00004290696,0.000200267,0.00003132,0.0005855872,8.958825e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001665737,"about_ca_system_score_gemma":0.00001666843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004805068,"about_ca_topic_score_gemma":0.00000637016,"domain_scores_codex":[0.9991697,0.00001203358,0.000305439,0.0001870462,0.00007477083,0.0002510245],"domain_scores_gemma":[0.9995911,0.00007427653,0.0000509833,0.0001126339,0.0001179454,0.00005303845],"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":[0.00008163194,0.00003108447,0.03391245,0.00117016,0.0008684787,0.00001639508,0.0003123521,0.3521575,0.3298295,0.0001725328,0.0002069497,0.281241],"study_design_scores_gemma":[0.0006183377,0.00007289428,0.003095181,0.0001543838,0.0000795348,0.0004102924,0.0001959385,0.9534099,0.03744396,0.0007623671,0.003575408,0.0001818242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5218384,0.002588176,0.4741733,0.00004687591,0.0008215689,0.0001280238,0.000004937433,0.0003956962,0.000002947929],"genre_scores_gemma":[0.9951838,0.0001510964,0.004510769,0.000005564664,0.00009522974,0.00002047643,7.652189e-7,0.00002566103,0.000006680495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6012524,"threshold_uncertainty_score":0.7837344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004906462915349697,"score_gpt":0.224586178042817,"score_spread":0.2196797151274673,"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."}}