{"id":"W4407935395","doi":"10.1080/17486025.2025.2468645","title":"Performance characterisation of machine learning models for geotechnical axial pile load capacity estimation: an enhanced GPR-based approach","year":2025,"lang":"en","type":"article","venue":"Geomechanics and Geoengineering","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Pile; Ground-penetrating radar; Geotechnical engineering; Geology; Structural engineering; Engineering; Civil engineering; Radar","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.0002362212,0.0001538122,0.0002246802,0.00008061858,0.00009130572,0.00002190722,0.00009670956,0.00009637033,0.000001970143],"category_scores_gemma":[0.00002788095,0.0001660315,0.00004846588,0.0002022913,0.00001105732,0.0001514852,0.00002242014,0.0001796979,4.28587e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003705778,"about_ca_system_score_gemma":0.00001627359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009199263,"about_ca_topic_score_gemma":6.369723e-7,"domain_scores_codex":[0.999253,0.000009189045,0.0002413661,0.0001965895,0.00009885218,0.0002010007],"domain_scores_gemma":[0.9996278,0.00005342573,0.00003945828,0.0001663086,0.00005891136,0.00005406957],"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":[0.000008724128,0.00002872596,0.000001229721,0.0003123383,0.00001184536,1.840128e-8,0.00004575249,0.9168112,0.05236431,0.004220892,8.408189e-7,0.02619414],"study_design_scores_gemma":[0.0002943121,0.00006906454,0.0001671295,0.00004078961,0.0000217141,4.427172e-7,0.000008003175,0.9818118,0.01542157,0.001880491,0.0001338699,0.0001508111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3561369,0.00003289877,0.6433623,0.00001207246,0.00005330459,0.0002042048,0.00001465136,0.0001354959,0.00004806933],"genre_scores_gemma":[0.9234967,0.00003095237,0.07616123,0.000007619173,0.00003198337,0.000183297,0.0000583775,0.00001919351,0.00001065121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5673597,"threshold_uncertainty_score":0.6770567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01891466918825093,"score_gpt":0.2262056065553647,"score_spread":0.2072909373671137,"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."}}