{"id":"W4213207553","doi":"10.3390/pr10020400","title":"Data-Driven Models for Forecasting Failure Modes in Oil and Gas Pipes","year":2022,"lang":"en","type":"article","venue":"Processes","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Pipeline transport; Pipeline (software); Artificial neural network; Multilayer perceptron; Product (mathematics); Computer science; Petroleum product; Engineering; Operations research; Petroleum engineering; Risk analysis (engineering); Petroleum; Artificial intelligence; Business; Mechanical engineering; Geology","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":[0.0001089534,0.00009132951,0.0001484313,0.00007337747,0.0001237137,0.00003798217,0.0002243199,0.00003169106,0.00002100757],"category_scores_gemma":[0.0001283882,0.00008295111,0.00001893081,0.0002470251,0.00001992772,0.0003224105,0.0001280497,0.0001603987,2.173785e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002777723,"about_ca_system_score_gemma":0.00002124215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000694203,"about_ca_topic_score_gemma":0.0007976301,"domain_scores_codex":[0.9994062,0.000009524508,0.0001427488,0.0001981724,0.00009114092,0.0001522236],"domain_scores_gemma":[0.9996431,0.0001322631,0.00001882418,0.0001409135,0.00003992163,0.00002493564],"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":[0.000009264043,0.000008675541,0.0001100615,0.001690506,0.00002765245,0.000001235778,0.0006369406,0.97861,0.0002067985,0.0001054387,0.0002024283,0.01839104],"study_design_scores_gemma":[0.0001130391,0.00001184708,0.000003209803,0.00002392634,0.00002426874,0.000007810367,0.00115822,0.9820802,0.0003460436,0.01360074,0.002520712,0.000109952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9756284,0.009108682,0.01135258,0.001568531,0.0001039427,0.0001550004,0.0006242871,0.0002935628,0.001165068],"genre_scores_gemma":[0.995083,0.0005632734,0.004070881,0.00001955598,0.0000338354,0.0000866934,0.00007907899,0.00001335572,0.00005031799],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01945466,"threshold_uncertainty_score":0.3382648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05316429593615335,"score_gpt":0.2507155950960455,"score_spread":0.1975512991598921,"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."}}