{"id":"W4400235064","doi":"10.11159/iccste24.146","title":"Explainable Machine Learning Model for Ballast Condition Assessment Using Ground Penetrating Radar Scans","year":2024,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Civil, Structural and Transportation Engineering","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Ground-penetrating radar; Ballast; Radar; Computer science; Remote sensing; Artificial intelligence; Marine engineering; Geology; Engineering; Electrical engineering; Telecommunications","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009439465,0.0007245851,0.0008008326,0.0008797529,0.0003479973,0.0009059704,0.001637952,0.001756818,0.002543111],"category_scores_gemma":[0.002971814,0.0004593709,0.0008469542,0.0006426586,0.0005669298,0.001104467,0.0007089252,0.001432111,0.0004470963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001022023,"about_ca_system_score_gemma":0.0007319186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01843574,"about_ca_topic_score_gemma":0.01261361,"domain_scores_codex":[0.9996444,0.00008863286,0.00002031216,0.0001430818,0.00004706016,0.0000565908],"domain_scores_gemma":[0.9984907,0.001055879,0.0001513566,0.00008267655,0.0001862052,0.0000331357],"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":[0.00008091542,0.00005022974,0.002195957,0.00002653068,0.00004578729,0.00008607162,0.00004496755,0.9750422,0.0008188945,0.003240126,0.0005048478,0.01786339],"study_design_scores_gemma":[0.000001971995,0.000005564578,0.0002064173,0.000001356722,0.000004108967,0.000005091479,0.000001599537,0.9987594,0.00006638005,0.0009086225,0.00003749668,0.000001998615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2161328,0.000672471,0.7775924,0.00108944,0.00008309085,0.00006905543,0.001207746,0.001215154,0.001937841],"genre_scores_gemma":[0.970265,0.0001927121,0.02496973,0.00008739502,0.00004340774,0.0001138833,0.0008077094,0.00004258697,0.003477437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01843574,"threshold_uncertainty_score":0.03665686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05119428782423947,"score_gpt":0.3244608959981514,"score_spread":0.2732666081739119,"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."}}