{"id":"W3120935587","doi":"10.1016/j.psep.2021.01.008","title":"Advanced intelligence frameworks for predicting maximum pitting corrosion depth in oil and gas pipelines","year":2021,"lang":"en","type":"article","venue":"Process Safety and Environmental Protection","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":148,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Kriging; Pitting corrosion; Pipeline transport; Multivariate adaptive regression splines; Artificial neural network; Pipeline (software); Mars Exploration Program; Extreme learning machine; Process (computing); Multivariate statistics; Petroleum engineering; Computer science; Environmental science; Engineering; Artificial intelligence; Corrosion; Machine learning; Regression analysis; Materials science; Metallurgy; Environmental engineering; Mechanical engineering","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":[0.0001305549,0.0001292768,0.0001527071,0.00003875358,0.0001637298,0.00002689171,0.00003409634,0.0002022911,0.00001445028],"category_scores_gemma":[0.00009370558,0.0001252439,0.00003247608,0.0001190392,0.00005996179,0.0002166942,0.00003039594,0.0004248106,6.404443e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006464091,"about_ca_system_score_gemma":0.000003543307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001757807,"about_ca_topic_score_gemma":0.0000781032,"domain_scores_codex":[0.9992365,0.00001797018,0.0002465231,0.0002570228,0.00008298852,0.0001589916],"domain_scores_gemma":[0.9997922,0.00005112576,0.00003694082,0.00006845078,0.000009653022,0.00004167328],"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":[0.0001120115,0.00002131891,0.001677094,0.0006191775,0.00001012911,0.000001297813,0.0006163543,0.2264499,0.01173116,0.000007732806,1.693558e-7,0.7587537],"study_design_scores_gemma":[0.0002898085,0.00005499238,0.001695027,0.0002896772,0.00002945243,0.00003793005,0.003615958,0.9557129,0.03070769,0.007170307,0.0001670305,0.0002292774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6024686,0.0022678,0.3943145,0.0003609436,0.0001702117,0.0001882979,0.00001344848,0.00009128753,0.000124965],"genre_scores_gemma":[0.9937935,0.004814108,0.00119423,0.00002143645,0.00004631126,0.00006150883,0.00002311129,0.00001371455,0.00003200737],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7585244,"threshold_uncertainty_score":0.5107296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007783882905270284,"score_gpt":0.2171377372344919,"score_spread":0.2093538543292216,"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."}}