{"id":"W4407004657","doi":"10.1021/acs.jcim.4c02060","title":"Can Focusing on One Deep Learning Architecture Improve Fault Diagnosis Performance?","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Agência Nacional do Petróleo, Gás Natural e Biocombustíveis; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Benchmark (surveying); Computer science; Deep learning; Convolutional neural network; Artificial intelligence; Machine learning; Baseline (sea); Set (abstract data type); Architecture; Fault (geology); Process (computing); Data set; Network architecture; Range (aeronautics); Artificial neural network; Data mining; 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":[0.001515422,0.002338003,0.001161347,0.000791627,0.0003720541,0.001210963,0.001461174,0.001566006,0.001763636],"category_scores_gemma":[0.005041265,0.0004816619,0.000875185,0.0004102218,0.0005620511,0.003183567,0.001119692,0.001888743,0.001065537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006645084,"about_ca_system_score_gemma":0.001281082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003491883,"about_ca_topic_score_gemma":0.009254739,"domain_scores_codex":[0.9994795,0.0001179711,0.00003497785,0.0001684253,0.00009156924,0.0001074567],"domain_scores_gemma":[0.998298,0.0005732903,0.0001748588,0.0003661707,0.0004648896,0.0001229671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006125568,0.0006289449,0.02306885,0.000577674,0.0005935425,0.0002265342,0.00016207,0.2943986,0.05745867,0.00254612,0.004217634,0.6155089],"study_design_scores_gemma":[0.0001008594,0.001540403,0.01124092,0.0002417502,0.0005698262,0.000242241,0.0002017796,0.9191743,0.05316458,0.00828671,0.005142619,0.00009406146],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5812314,0.007246548,0.3929633,0.003500875,0.0004728395,0.0001833873,0.0004043198,0.005102514,0.008894781],"genre_scores_gemma":[0.9249888,0.001178422,0.07089206,0.0004691432,0.00007449814,0.00006092835,0.0003805209,0.0001336396,0.001821952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003491883,"threshold_uncertainty_score":0.008014381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006972734104036741,"score_gpt":0.2090397904825544,"score_spread":0.2020670563785177,"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."}}