{"id":"W4391956969","doi":"10.1016/j.psep.2024.02.051","title":"Predicting failure pressure of corroded gas pipelines: A data-driven approach using machine learning","year":2024,"lang":"en","type":"article","venue":"Process Safety and Environmental Protection","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Hong Kong Polytechnic University","keywords":"Pipeline (software); Pipeline transport; Interpretability; Dependability; Resource (disambiguation); GRASP; Integrity management; Engineering; Risk analysis (engineering); Computer science; Reliability engineering; Machine learning; 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":[0.00019099,0.000147188,0.0001788155,0.00006366878,0.0001466778,0.0000350325,0.0000820101,0.0001225364,0.00002650189],"category_scores_gemma":[0.00002747535,0.0001266372,0.00003123065,0.0001294186,0.0001023865,0.0003770853,0.00008342983,0.0004583166,7.500971e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002956859,"about_ca_system_score_gemma":0.00000430618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001716475,"about_ca_topic_score_gemma":0.00001788476,"domain_scores_codex":[0.9991673,0.00003851683,0.000232873,0.0003037694,0.0001361284,0.0001214243],"domain_scores_gemma":[0.9997769,0.00001830466,0.0000366028,0.0001236558,0.000004844751,0.00003970243],"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":[0.0000383459,0.00001640008,0.001363238,0.002616541,0.0001589615,8.355542e-7,0.001010489,0.9710903,0.01417353,0.000007995308,6.814071e-7,0.009522726],"study_design_scores_gemma":[0.0001027814,0.00002589887,0.0001579902,0.0001171056,0.0001710172,0.00006088731,0.0009274077,0.9968367,0.001060838,0.0000947082,0.0003171049,0.0001275956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6631712,0.01050401,0.3246166,0.0001064744,0.0001510683,0.0006571853,0.000239546,0.0004114512,0.0001425108],"genre_scores_gemma":[0.9981663,0.0007748889,0.0008074294,0.000001928852,0.00006209041,0.000009659861,0.0001309739,0.00002026359,0.00002641498],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3349952,"threshold_uncertainty_score":0.5164113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01575146156128851,"score_gpt":0.2155777395735589,"score_spread":0.1998262780122704,"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."}}