{"id":"W2559408831","doi":"10.2355/isijinternational.isijint-2016-368","title":"Development of an Artificial Neural Network to Predict Sulphide Capacities of CaO–SiO<sub>2</sub>–Al<sub>2</sub>O<sub>3</sub>–MgO Slag System","year":2016,"lang":"en","type":"article","venue":"ISIJ International","topic":"Metallurgical Processes and Thermodynamics","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hatch (Canada); University of Toronto","funders":"","keywords":"Ferroalloy; Artificial neural network; Smelting; Mean squared error; Refining (metallurgy); Slag (welding); Correlation coefficient; Metallurgy; Process engineering; Biological system; Mathematics; Computer science; Materials science; Engineering; Statistics; Machine learning","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":["metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.002196857,0.00213345,0.002530387,0.001196264,0.0006278409,0.0004407998,0.002922666,0.001064355,0.0006788785],"category_scores_gemma":[0.0005571261,0.001933283,0.0009465723,0.001328171,0.0006859799,0.001537936,0.000985495,0.001049008,0.0005713835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001592557,"about_ca_system_score_gemma":0.0006285612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005401866,"about_ca_topic_score_gemma":0.001856762,"domain_scores_codex":[0.9863038,0.0004252264,0.004595716,0.002222289,0.00391486,0.002538092],"domain_scores_gemma":[0.9929,0.0008573977,0.001478688,0.001748299,0.001748061,0.001267563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001415672,0.0008117608,0.0002648104,0.001492,0.002231089,0.0002933407,0.002508221,0.07519584,0.847334,0.04173941,0.005999221,0.02071459],"study_design_scores_gemma":[0.00742307,0.00134085,0.008682002,0.005467011,0.0009139898,0.0006330752,0.0008067802,0.669216,0.2157117,0.004596687,0.07828836,0.00692043],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9540638,0.001360719,0.02636122,0.0005135394,0.006940447,0.001676406,0.001315975,0.001023278,0.006744571],"genre_scores_gemma":[0.9914738,0.0005463978,0.002500315,0.0003007834,0.002996108,0.0004468729,0.0006795664,0.0005350733,0.0005210866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6316223,"threshold_uncertainty_score":0.9991406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01372130401389711,"score_gpt":0.214455022812486,"score_spread":0.2007337187985889,"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."}}