{"id":"W4412402468","doi":"10.1038/s41529-025-00638-y","title":"Corrosion type identification in flanged joints using recurrent neural networks on electrochemical noise measurements","year":2025,"lang":"en","type":"article","venue":"npj Materials Degradation","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Electrochemical noise; Autoencoder; Corrosion; Flange; Computer science; Artificial intelligence; Artificial neural network; Identification (biology); Cluster analysis; Unsupervised learning; Pattern recognition (psychology); Classifier (UML); Engineering; Structural engineering; Materials science; Metallurgy; Electrochemistry","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":[0.0002510342,0.0001284931,0.0001807824,0.0001571289,0.00005249969,0.00007901441,0.00009179825,0.0001390798,0.00006010294],"category_scores_gemma":[0.0001095327,0.000119761,0.00003419202,0.000372812,0.00001498543,0.0001150241,0.00001401448,0.0001451863,0.000009294915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002957123,"about_ca_system_score_gemma":0.000009079966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003830505,"about_ca_topic_score_gemma":0.00004224928,"domain_scores_codex":[0.9990411,0.00008846416,0.0003664579,0.0001896898,0.0001526891,0.0001616339],"domain_scores_gemma":[0.9996603,0.00002422376,0.00005114069,0.0001652907,0.00007628075,0.00002274751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007124356,0.00001903919,0.0005162034,0.00004524441,0.00001082241,2.589997e-7,0.00001883864,0.01594729,0.9815174,0.0000309365,0.00008293636,0.00173974],"study_design_scores_gemma":[0.0001893116,0.00001500523,0.008683316,0.0001094793,0.00003923051,7.715254e-7,0.000009106408,0.2275761,0.763105,0.000143551,0.0000145105,0.0001146158],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941242,0.00008628862,0.003692276,0.00005165737,0.001720916,0.0001855647,0.000003243995,0.00007867036,0.00005718818],"genre_scores_gemma":[0.9994618,0.00004691548,0.0001317058,0.00002960341,0.0000647422,0.000009550458,0.0002166714,0.000009883971,0.00002918644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2184124,"threshold_uncertainty_score":0.4883712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03300919083589916,"score_gpt":0.2724956955395434,"score_spread":0.2394865047036443,"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."}}