{"id":"W3121549777","doi":"10.1139/cgj-2020-0686","title":"A hybrid GMDH neural network and logistic regression framework for state parameter–based liquefaction evaluation","year":2021,"lang":"en","type":"article","venue":"Canadian Geotechnical Journal","topic":"Geotechnical Engineering and Soil Mechanics","field":"Engineering","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Liquefaction; Artificial neural network; Probabilistic logic; Logistic regression; Cone penetration test; Geotechnical engineering; Mathematics; Computer science; Statistics; Engineering; Machine learning","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":[0.0006569124,0.0002094415,0.0002547946,0.0001235341,0.0002101317,0.0001445101,0.0001301647,0.0002505257,0.00004033169],"category_scores_gemma":[0.00141217,0.0002076222,0.0001161232,0.0001921139,0.00003052208,0.00008620391,0.00001604911,0.0009862421,0.000003090288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003814753,"about_ca_system_score_gemma":0.0003215191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001415944,"about_ca_topic_score_gemma":0.0003036217,"domain_scores_codex":[0.9985101,0.00007265753,0.0003497046,0.0002309267,0.0002473563,0.000589209],"domain_scores_gemma":[0.9984811,0.0003303835,0.00005601548,0.0002521671,0.0001971224,0.000683225],"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":[0.00001056219,0.000005420793,0.000003119141,0.00003184706,0.00001830926,0.00007304687,0.000004778368,0.9374912,0.00008663709,0.0003419414,0.000958161,0.06097494],"study_design_scores_gemma":[0.0003168395,0.00008326172,0.0002295805,0.0002169904,0.00005423055,0.0003067259,0.000005315458,0.9560349,0.0004067175,0.03817042,0.003937959,0.0002370462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1114297,0.001740074,0.8838171,0.001050515,0.001309746,0.0003261397,0.00003761892,0.0002714546,0.00001763248],"genre_scores_gemma":[0.9869588,0.0001496589,0.01215959,0.0003149055,0.0002854303,0.0000419542,0.00002766005,0.00005028182,0.00001172932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8755291,"threshold_uncertainty_score":0.8466588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02915039589762319,"score_gpt":0.2607796572045701,"score_spread":0.2316292613069469,"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."}}