{"id":"W4381853033","doi":"10.1016/j.ijpvp.2023.105000","title":"Forecasting pipeline safety and remaining life with machine learning methods and SHAP interaction values","year":2023,"lang":"en","type":"article","venue":"International Journal of Pressure Vessels and Piping","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Alberta Energy; University of Calgary","funders":"","keywords":"Pipeline (software); Pipeline transport; Line (geometry); Computer science; Artificial intelligence; Engineering; Reliability engineering; Data mining; Mathematics; Mechanical engineering; Geometry","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":[0.0009008475,0.0001205709,0.0002442743,0.000231016,0.0001086646,0.0001389241,0.00008719262,0.00006124216,0.00002240856],"category_scores_gemma":[0.0005226566,0.00008903511,0.0000419158,0.000125603,0.00005165779,0.000384756,0.00006094899,0.000459536,2.196542e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000144531,"about_ca_system_score_gemma":0.000009610199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003111582,"about_ca_topic_score_gemma":0.000009606006,"domain_scores_codex":[0.9991111,0.00009085552,0.000367821,0.0001213548,0.0001951236,0.0001137863],"domain_scores_gemma":[0.9989806,0.0005426292,0.0001564985,0.0000382524,0.000197273,0.00008469428],"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":[0.0007368734,0.00001662918,0.02031578,0.0006100743,0.002996043,0.0001234987,0.01014842,0.5923441,0.01314206,0.0004800973,0.0001929565,0.3588935],"study_design_scores_gemma":[0.0004218129,0.0000614604,0.002998543,0.0005024219,0.0001535658,0.0004289751,0.0009394172,0.9864736,0.0007917938,0.0005817473,0.006511325,0.0001353924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9114017,0.007213631,0.0780227,0.001696268,0.0008968842,0.00008235078,0.00001331571,0.0001111815,0.0005619266],"genre_scores_gemma":[0.9894525,0.002825458,0.007291578,0.00003810473,0.0002948094,6.176663e-7,0.00000504088,0.0000144431,0.00007747643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3941294,"threshold_uncertainty_score":0.3630746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0288237022378997,"score_gpt":0.3120427222435191,"score_spread":0.2832190200056194,"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."}}