{"id":"W4366249108","doi":"10.1139/cgj-2022-0131","title":"Fast stratification of geological cross-section from CPT results with missing data using multitask and modified Bayesian compressive sensing","year":2023,"lang":"en","type":"article","venue":"Canadian Geotechnical Journal","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Cone penetration test; Depth sounding; Stratification (seeds); Geology; Bayesian probability; Autocorrelation; Missing data; Geotechnical engineering; Data assimilation; Soil science; Remote sensing; Computer science; Meteorology; Mathematics; Statistics; Artificial intelligence; Machine learning; Geography","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":[0.0002705,0.0001260525,0.0001938575,0.0001245316,0.000260499,0.0001309683,0.0002073638,0.0001504649,0.000005706321],"category_scores_gemma":[0.000136377,0.0001120719,0.00002556075,0.0003209776,0.0001482603,0.0001666021,0.0000401985,0.0004518733,0.000001767641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007542188,"about_ca_system_score_gemma":0.00009264019,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007301382,"about_ca_topic_score_gemma":0.00153937,"domain_scores_codex":[0.9989236,0.00005355524,0.0003515246,0.0002539649,0.0001420197,0.0002753563],"domain_scores_gemma":[0.9989093,0.0001698799,0.0001005344,0.00037141,0.0000858969,0.0003630119],"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":[0.0000492035,0.00001825111,0.0002849865,0.00002316868,0.0000779083,0.00009857467,0.0001351776,0.7962379,0.1250962,0.0001777282,0.0002574323,0.0775435],"study_design_scores_gemma":[0.0003311877,0.00002360561,0.03746099,0.00008043928,0.00002899205,0.0000843544,0.00006794358,0.9593509,0.0005780879,0.001633747,0.0002125532,0.0001471839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6874686,0.00004731558,0.3113937,0.0003155865,0.00009395815,0.0001416161,0.0003353913,0.0001027446,0.0001011212],"genre_scores_gemma":[0.963639,0.0000164894,0.03600175,0.00001513074,0.0001879357,0.000001048349,0.0001161121,0.00001827344,0.000004278865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2761704,"threshold_uncertainty_score":0.9993091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0659042466965721,"score_gpt":0.303482901178392,"score_spread":0.2375786544818199,"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."}}