{"id":"W4399357348","doi":"10.1002/cjce.25355","title":"Classification of pitting corrosion damage in process facilities using supervised machine learning","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Structural Integrity and Reliability Analysis","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pitting corrosion; Corrosion; Process (computing); Computer science; Artificial intelligence; Metallurgy; Process engineering; Materials science; Machine learning; Environmental science; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003180736,0.0001045742,0.0001983639,0.0002559227,0.00003152427,0.00005025669,0.0001739128,0.00008770073,0.00004083779],"category_scores_gemma":[0.0002394747,0.00007895927,0.00009454726,0.0003918433,0.0000522282,0.0001476635,0.000005777437,0.0007485635,5.755567e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002347446,"about_ca_system_score_gemma":0.0001088052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001367866,"about_ca_topic_score_gemma":0.000489736,"domain_scores_codex":[0.9992296,0.00001572769,0.0003802704,0.0000658991,0.0001313944,0.0001771825],"domain_scores_gemma":[0.9996014,0.0001178583,0.00003256353,0.00007273639,0.00006845409,0.0001069847],"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":[0.000002438443,0.00000102925,0.0006337456,0.0003535972,0.0000213431,0.0000094929,0.001458346,0.6720452,0.3249972,0.00009337345,0.000003409027,0.0003809044],"study_design_scores_gemma":[0.0000600516,0.000006662628,0.0002321766,0.0003848201,0.00002670888,0.00003423696,0.0002279127,0.936765,0.06198423,0.0001142698,0.00008126167,0.00008264654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971758,0.001480403,0.0009504788,0.00009628873,0.0001843257,0.00003499496,0.000006575985,0.00002387868,0.00004732987],"genre_scores_gemma":[0.9996844,0.000008102174,0.0002139216,0.000002374128,0.00006402946,6.710637e-7,0.000002864759,0.00001570949,0.000007923916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2647198,"threshold_uncertainty_score":0.3252178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01605749554550115,"score_gpt":0.219050290184904,"score_spread":0.2029927946394028,"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."}}