{"id":"W3141865877","doi":"10.1061/(asce)ps.1949-1204.0000557","title":"Gradient Boosting Coupled with Oversampling Model for Prediction of Concrete Pipe-Joint Infiltration Using Designwise Data Set","year":2021,"lang":"en","type":"article","venue":"Journal of Pipeline Systems Engineering and Practice","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Support vector machine; Random forest; Oversampling; Gradient boosting; Boosting (machine learning); Computer science; Infiltration (HVAC); Machine learning; Artificial intelligence; Test set; Test data; Data mining","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":[0.001172026,0.0001564696,0.0003308373,0.0001086214,0.00005167671,0.00006674386,0.00007915815,0.00006995435,3.811367e-7],"category_scores_gemma":[0.001124911,0.0001400685,0.00003740323,0.0001232052,0.00001027297,0.0007952347,0.00002374273,0.0002386138,3.881741e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007914357,"about_ca_system_score_gemma":0.000102704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001581259,"about_ca_topic_score_gemma":6.868732e-7,"domain_scores_codex":[0.9987934,0.00003015737,0.0006438055,0.0001311191,0.0002188138,0.0001826841],"domain_scores_gemma":[0.9983529,0.0003998218,0.0003812516,0.0001984053,0.0005909556,0.00007665157],"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":[0.00006540181,0.000002363457,0.00002584325,0.0004967249,0.0001046124,0.00001368467,0.0003935965,0.8347653,0.1639305,0.00003948091,0.00007352779,0.0000890239],"study_design_scores_gemma":[0.0007240815,0.00007030848,0.00001777393,0.0008623917,0.0002583025,0.001457262,0.0007617126,0.9907347,0.004261062,0.000003620318,0.0007255777,0.0001232372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07668267,0.00151498,0.9206513,0.00001771833,0.0008578284,0.0001436139,0.00008149302,0.00003221224,0.00001823886],"genre_scores_gemma":[0.8782481,0.0001489946,0.1209058,0.000005349246,0.0006188552,0.000002487497,0.00002746664,0.00003551073,0.000007425512],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8015655,"threshold_uncertainty_score":0.5711828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07295837534124122,"score_gpt":0.2752210074488664,"score_spread":0.2022626321076252,"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."}}