{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006449138,0.00007945705,0.00009670196,0.00009839962,0.0005082367,0.0001679669,0.00003788742,0.00004079675,0.00006444674],"category_scores_gemma":[0.00006413826,0.00008232737,0.00003537618,0.0002523388,0.00001781219,0.0001012904,0.00003645018,0.0001425922,0.000001693544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004326991,"about_ca_system_score_gemma":0.00001054886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007242662,"about_ca_topic_score_gemma":0.00003130687,"domain_scores_codex":[0.9991219,0.00002104729,0.0002331538,0.0002800865,0.0001839642,0.000159856],"domain_scores_gemma":[0.9996278,0.00001850721,0.00005866224,0.0002011083,0.00004813233,0.00004575967],"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":[0.000008711209,0.00001403516,0.0005612187,0.0001995734,0.00001680989,0.00003984919,0.001748229,0.9246963,0.01667973,0.00003240018,0.01381348,0.04218967],"study_design_scores_gemma":[0.0001313924,0.00002900058,0.00002333142,0.00003123509,0.00001574707,0.0002304859,0.0005135591,0.5613753,0.01071072,0.002252226,0.4244806,0.0002065052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4771696,0.0005948667,0.5015057,0.0002098166,0.01816351,0.0002885179,0.000005854712,0.0006356595,0.001426521],"genre_scores_gemma":[0.9888601,0.000004123096,0.003134056,0.000004924473,0.0001155695,0.00009535794,0.00005124224,0.00002294487,0.007711698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5116905,"threshold_uncertainty_score":0.3908997,"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."}}