{"id":"W4403224968","doi":"10.1016/j.oceaneng.2024.119433","title":"Rapid failure risk analysis of corroded gas pipelines using machine learning","year":2024,"lang":"en","type":"article","venue":"Ocean Engineering","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Pipeline and Hazardous Materials Safety Administration; Hong Kong Polytechnic University","keywords":"Pipeline transport; Forensic engineering; Petroleum engineering; Corrosion; Engineering; Marine engineering; Environmental science; Materials science; Metallurgy; 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":[0.0002539621,0.0002619187,0.0005016555,0.0008629895,0.00005587406,0.00006593567,0.0001608089,0.0001425576,0.0002230516],"category_scores_gemma":[0.0001469071,0.0002363967,0.0004752152,0.002220936,0.00003182105,0.0001593854,0.0000327809,0.0006426009,0.000006113407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008314753,"about_ca_system_score_gemma":0.000009905656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001734108,"about_ca_topic_score_gemma":0.00005065553,"domain_scores_codex":[0.9988178,0.00002789544,0.0004191074,0.0002587315,0.0002005239,0.0002759495],"domain_scores_gemma":[0.9994562,0.0001378432,0.00003731601,0.0002419922,0.00004419153,0.00008248285],"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":[0.000001964557,0.000003646706,0.001364163,0.0002276655,0.001790676,0.000008273708,0.0003032808,0.9820161,0.01187115,0.00005836036,0.00003544073,0.00231922],"study_design_scores_gemma":[0.00005874312,0.00001159389,0.0005114386,0.00008841653,0.002013046,0.000006811441,0.00008780083,0.9885616,0.006567633,0.00001944302,0.001826034,0.0002474291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9424734,0.006277832,0.04973711,0.00002653392,0.0004440325,0.00006513215,0.00007495016,0.0008237307,0.00007731815],"genre_scores_gemma":[0.9950866,0.0006615735,0.003978875,0.000002344126,0.0001180048,8.236336e-7,0.00004965903,0.00005284583,0.00004932323],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0526132,"threshold_uncertainty_score":0.9639977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00811398863847363,"score_gpt":0.2063747041550809,"score_spread":0.1982607155166073,"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."}}