{"id":"W2921534671","doi":"10.1016/j.oceaneng.2019.02.009","title":"Dynamic risk assessment of subsea pipelines leak using precursor data","year":2019,"lang":"en","type":"article","venue":"Ocean Engineering","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":94,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada","keywords":"Subsea; Pipeline transport; Integrity management; Risk assessment; Computer science; Risk analysis (engineering); Bayesian network; Reliability engineering; Bayesian probability; Risk management; Pipeline (software); Failure mode and effects analysis; Engineering; Machine learning; Marine engineering; Business; Computer security; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001953438,0.0001426107,0.0003755415,0.0002939786,0.00004495047,0.00007956629,0.001140582,0.00005562392,0.0001544687],"category_scores_gemma":[0.0007583881,0.0001142506,0.0001161508,0.000772057,0.00002097033,0.0004896201,0.000308307,0.0001636855,0.00005308905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003813747,"about_ca_system_score_gemma":0.00005612569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004479616,"about_ca_topic_score_gemma":0.00002926671,"domain_scores_codex":[0.9978669,0.0000595219,0.0005749558,0.0004577816,0.0008199128,0.0002209442],"domain_scores_gemma":[0.9975963,0.0004724986,0.0002413967,0.001465641,0.0001521243,0.00007203624],"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":[0.00000514447,0.00002585009,0.1089938,0.00001689621,0.0000620397,0.000002020968,0.00007760031,0.881765,0.001675122,0.0001419604,0.0002071127,0.007027385],"study_design_scores_gemma":[0.0001474649,0.00001427299,0.04035984,0.00002476605,0.00004985113,0.000002108433,0.0001331224,0.9573021,0.00007483256,0.000237448,0.001524611,0.0001296066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8074883,0.0002381579,0.1912239,0.00006656282,0.0003378494,0.00009726692,0.00009801604,0.00003648284,0.0004135525],"genre_scores_gemma":[0.9680893,0.0001470389,0.03123954,0.000004906385,0.0000333233,2.310381e-7,0.00002369485,0.00001760555,0.000444399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.160601,"threshold_uncertainty_score":0.4659005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06488762943257863,"score_gpt":0.3776938358609952,"score_spread":0.3128062064284166,"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."}}