{"id":"W4290830415","doi":"10.1038/s41598-022-16830-y","title":"Semi-supervised learning framework for oil and gas pipeline failure detection","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Water Systems and Optimization","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pipeline (software); Classifier (UML); Machine learning; Pipeline transport; Scalability; Artificial intelligence; Data mining; Supervised learning; Missing data; Artificial neural network; Database; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002353559,0.000885456,0.001456639,0.0009054633,0.0004864213,0.0008971303,0.002644452,0.001224088,0.001347138],"category_scores_gemma":[0.00350155,0.0005002348,0.001169235,0.0009071222,0.0006773463,0.001127666,0.001304954,0.001797675,0.0006480202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008999912,"about_ca_system_score_gemma":0.001988175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007037176,"about_ca_topic_score_gemma":0.006992952,"domain_scores_codex":[0.9988105,0.0004344372,0.00007631497,0.0002881973,0.0002808686,0.0001096713],"domain_scores_gemma":[0.9977425,0.0008799761,0.0002335577,0.0003322929,0.0007202105,0.00009142152],"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":[0.0001810911,0.0003262299,0.002385058,0.0001344682,0.0001829302,0.00008144898,0.0001027784,0.7330182,0.002276999,0.005811381,0.003692425,0.251807],"study_design_scores_gemma":[0.00000253159,0.00002085714,0.0001167834,0.000002332549,0.00000369848,0.000007178358,0.000004664343,0.9975642,0.0003168136,0.001748196,0.00020954,0.000003212979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0134827,0.0002590298,0.9839279,0.0001561447,0.00003141147,0.0000640511,0.0001696306,0.001333012,0.0005762162],"genre_scores_gemma":[0.6417184,0.0003545101,0.3505281,0.000278082,0.0001842847,0.0006110627,0.001838875,0.0001591816,0.00432755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007037176,"threshold_uncertainty_score":0.01399243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0074333784261703,"score_gpt":0.1944970863505066,"score_spread":0.1870637079243363,"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."}}