{"id":"W4412605934","doi":"10.1016/j.istruc.2025.109765","title":"Interpretable natural gradient boosting model for probabilistic response evaluation of RC columns under blast loads","year":2025,"lang":"en","type":"article","venue":"Structures","topic":"Structural Response to Dynamic Loads","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; McMaster University","funders":"National Natural Science Foundation of China","keywords":"Boosting (machine learning); Probabilistic logic; Gradient boosting; Computer science; Structural engineering; Artificial intelligence; Machine learning; Engineering; Random forest","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":[0.0006036822,0.0002317574,0.0002788234,0.0002261513,0.00008479413,0.00004160039,0.0002448116,0.0001140809,0.0000397133],"category_scores_gemma":[0.001527674,0.0002144952,0.0001113994,0.0002600982,0.0000988299,0.0001059178,0.0000584685,0.0001855435,6.683657e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005134502,"about_ca_system_score_gemma":0.0002924876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001575938,"about_ca_topic_score_gemma":0.00009694579,"domain_scores_codex":[0.9985386,0.000110962,0.0003923246,0.0002704187,0.0003569984,0.0003307245],"domain_scores_gemma":[0.9987151,0.000527727,0.00006996816,0.0003373724,0.0003032201,0.00004663666],"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":[0.0008229701,0.000003846361,0.0000348209,0.000161461,0.0001091615,2.842833e-7,0.0005057912,0.9312544,0.05684554,0.004766908,0.0004678598,0.00502699],"study_design_scores_gemma":[0.0007999394,0.00003357572,0.007098832,0.00008454776,0.0001398194,0.000004570897,0.00009349282,0.9286243,0.005152616,0.05774516,0.00004224649,0.0001809536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9740342,0.0005589557,0.02272485,0.00005591647,0.0008459144,0.0009000241,0.00006884827,0.0001540785,0.0006572375],"genre_scores_gemma":[0.9960214,0.000001958703,0.003228374,0.00003992579,0.00002580377,0.00009274802,0.00002007537,0.00003044544,0.0005392418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05297825,"threshold_uncertainty_score":0.8746861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01598803039018773,"score_gpt":0.2889306007553026,"score_spread":0.2729425703651149,"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."}}