{"id":"W2111420168","doi":"10.1139/t06-077","title":"Modeling the mechanical behavior of railway ballast using artificial neural networks","year":2006,"lang":"en","type":"article","venue":"Canadian Geotechnical Journal","topic":"Railway Engineering and Dynamics","field":"Engineering","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Ballast; Geotechnical engineering; Artificial neural network; Constitutive equation; Structural engineering; Engineering; Hardening (computing); Strain hardening exponent; Deformation (meteorology); Finite element method; Geology; Materials science; Computer science; Composite material","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002691359,0.0005740796,0.0003113048,0.0003697533,0.000172942,0.0004384164,0.0005246503,0.0007841394,0.0009389324],"category_scores_gemma":[0.0007473546,0.000317645,0.0003239315,0.0003751109,0.0002073091,0.0005813972,0.0001714316,0.0003423297,0.0002134304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004679218,"about_ca_system_score_gemma":0.000359665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01446272,"about_ca_topic_score_gemma":0.01193673,"domain_scores_codex":[0.9998932,0.0000241234,0.000009707496,0.00002840047,0.00002846636,0.00001614563],"domain_scores_gemma":[0.9997595,0.0001303298,0.00003797953,0.00001172945,0.00005439206,0.000006121681],"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":[0.00001685835,0.00001717248,0.0007551418,0.00001328823,0.000009993413,0.0000182559,0.000007310313,0.992392,0.001018183,0.0001405675,0.00006309945,0.005548147],"study_design_scores_gemma":[6.554673e-7,0.000004175949,0.0001752,8.006658e-7,0.000001176235,0.000001662574,0.000001126543,0.9995505,0.0001601219,0.00007974941,0.00002388577,9.876179e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5119643,0.0006702949,0.4807613,0.0002417906,0.00005195208,0.00005878196,0.0003617525,0.000767682,0.005122194],"genre_scores_gemma":[0.978151,0.0002891649,0.01915263,0.00001839858,0.00001212149,0.00007635156,0.0002263502,0.00001237569,0.002061595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01446272,"threshold_uncertainty_score":0.02875704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01274782890872336,"score_gpt":0.201148480531505,"score_spread":0.1884006516227817,"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."}}