{"id":"W4411711766","doi":"10.1016/j.jma.2025.06.005","title":"Multi-scale simplified residual convolutional neural network model for predicting compositions of binary magnesium alloys","year":2025,"lang":"en","type":"article","venue":"Journal of Magnesium and Alloys","topic":"Aluminum Alloy Microstructure Properties","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"China Postdoctoral Science Foundation; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Materials science; Magnesium; Convolutional neural network; Residual; Binary number; Scale (ratio); Artificial neural network; Metallurgy; Artificial intelligence; Computer science; Algorithm; Mathematics; Physics","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":[0.0003225283,0.0002371035,0.0004315152,0.0001675469,0.0001774569,0.00004265226,0.0002360933,0.0001413757,0.00001225848],"category_scores_gemma":[0.00003400434,0.0002134538,0.0001527683,0.0001447218,0.000164107,0.0002575426,0.00008187113,0.0002826491,4.245174e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005018286,"about_ca_system_score_gemma":0.0001005311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006992335,"about_ca_topic_score_gemma":0.00002104567,"domain_scores_codex":[0.9985005,0.00004197259,0.0007597766,0.0001643041,0.0001944786,0.0003389489],"domain_scores_gemma":[0.9991112,0.0001449254,0.0001977363,0.0001445805,0.0003014107,0.000100183],"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":[0.0003294995,0.00006704551,0.004866822,0.0006682008,0.00009133868,0.000007014608,0.0003839483,0.5818666,0.40749,0.0001408397,0.003788167,0.0003005655],"study_design_scores_gemma":[0.002097354,0.000253159,0.02541733,0.0000952224,0.00027714,0.0001033518,0.0002090447,0.9669943,0.003648247,0.0004291337,0.0002274765,0.0002482629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9566756,0.004207324,0.03688708,0.0005885032,0.0009416462,0.0003408336,0.0001049217,0.00007576137,0.000178313],"genre_scores_gemma":[0.9608123,0.00004414143,0.03812698,0.0001100877,0.0003434715,0.00001094393,0.00001289662,0.00003380074,0.0005054168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4038418,"threshold_uncertainty_score":0.8704395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01404910377760754,"score_gpt":0.2320831819249561,"score_spread":0.2180340781473486,"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."}}