{"id":"W2896174059","doi":"10.1139/cgj-2017-0709","title":"A Bayesian unsupervised learning approach for identifying soil stratification using cone penetration data","year":2018,"lang":"en","type":"article","venue":"Canadian Geotechnical Journal","topic":"Landslides and related hazards","field":"Environmental Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Pattern recognition (psychology); Bayesian probability; Probabilistic logic; Artificial intelligence; Data mining; Python (programming language); Feature vector; Stratification (seeds); MATLAB; Cone penetration test; Mathematics; Geology; Geotechnical engineering","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":[0.0008441313,0.0001139973,0.0001210118,0.00007902066,0.0009090218,0.0002449416,0.0004982424,0.0001945236,0.0006795619],"category_scores_gemma":[0.0001113138,0.0001000475,0.00004884793,0.0002191391,0.0001658186,0.0004274698,0.00007260883,0.0004375597,0.000026788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003593395,"about_ca_system_score_gemma":0.0002102177,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008891541,"about_ca_topic_score_gemma":0.009248314,"domain_scores_codex":[0.9986818,0.00006263673,0.0003045274,0.0003200251,0.00022795,0.0004030623],"domain_scores_gemma":[0.9990494,0.00001877635,0.0001208216,0.0003146107,0.00003576779,0.0004605935],"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":[0.0001866709,0.0001917071,0.008479138,0.00006797878,0.0002169528,0.00008878364,0.001171918,0.7108014,0.129784,0.0006565147,0.01791464,0.1304403],"study_design_scores_gemma":[0.0003427608,0.00008061565,0.001593446,0.00002130102,0.00004570037,0.0002267764,0.0001151374,0.9896036,0.0002415182,0.0004358622,0.007114173,0.0001790986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08415869,0.00007477167,0.9129195,0.0004741179,0.000224197,0.0003485165,0.00002553396,0.00004037261,0.001734268],"genre_scores_gemma":[0.984174,0.00001814349,0.0150628,0.0001388389,0.000341805,0.000003629413,0.0001098301,0.00001981491,0.0001311122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9000154,"threshold_uncertainty_score":0.9977083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05501350137834433,"score_gpt":0.2800192973503038,"score_spread":0.2250057959719595,"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."}}