{"id":"W4361220749","doi":"10.1016/j.istruc.2023.03.109","title":"Data-driven ensemble learning approach for optimal design of cantilever soldier pile retaining walls","year":2023,"lang":"en","type":"article","venue":"Structures","topic":"Geotechnical Engineering and Analysis","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Polytechnique Montréal","funders":"","keywords":"Pile; Cantilever; Constraint (computer-aided design); Structural engineering; Ensemble learning; Retaining wall; Engineering; Stability (learning theory); Computer science; Geotechnical engineering; Artificial intelligence; Machine learning; Mechanical engineering","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":[0.0001979,0.0001399092,0.0002513113,0.0001166067,0.00005752603,0.00001984121,0.0002883845,0.00009370175,0.00002304487],"category_scores_gemma":[0.0001134552,0.0001295634,0.00006683917,0.0002534061,0.00002335027,0.00005494112,0.0000806398,0.0001866404,0.00000311719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001314063,"about_ca_system_score_gemma":0.00001249923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009301187,"about_ca_topic_score_gemma":5.730249e-7,"domain_scores_codex":[0.9991471,0.00001593447,0.0001973338,0.0002175978,0.00013199,0.0002900579],"domain_scores_gemma":[0.9994769,0.00009534601,0.00003087889,0.0003192079,0.0000288731,0.00004886137],"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":[0.000004746693,0.000001639588,0.00001574163,0.0001015192,0.00009912572,0.000001281841,0.00008918259,0.9844407,0.01043292,0.00006362276,0.002134045,0.002615484],"study_design_scores_gemma":[0.0001359701,0.00002291297,0.0001513446,0.00001192502,0.00005408249,0.000002098067,0.00007832472,0.9952786,0.002633865,0.0001213858,0.001360734,0.0001487889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03660528,0.0001298975,0.9621068,0.000007815687,0.00008244886,0.0001492206,0.00007101378,0.0006138504,0.0002337213],"genre_scores_gemma":[0.9307153,0.00002405905,0.06870963,0.000002977451,0.0000730908,0.00001447798,0.0002270352,0.00004147858,0.0001919724],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.89411,"threshold_uncertainty_score":0.528344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03965414298740726,"score_gpt":0.2509406362091793,"score_spread":0.2112864932217721,"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."}}