{"id":"W3200667102","doi":"10.1016/j.watres.2021.117680","title":"Failure modeling of water distribution pipelines using meta-learning algorithms","year":2021,"lang":"en","type":"article","venue":"Water Research","topic":"Water Systems and Optimization","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Pipeline transport; Urbanization; Environmental science; Residual; Index (typography); Environmental engineering; Pipe network analysis; Engineering; Civil engineering; Computer science; Petroleum engineering; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0008379965,0.000120845,0.0002527229,0.0001057909,0.0001378286,0.00009638073,0.0001071173,0.00009833793,0.0001552976],"category_scores_gemma":[0.0000221582,0.00007405609,0.00009639584,0.0001761876,0.00002335559,0.000197576,0.0001218184,0.0002954734,0.00003633062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006233084,"about_ca_system_score_gemma":0.00001277982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001577558,"about_ca_topic_score_gemma":0.00003526661,"domain_scores_codex":[0.9984359,0.0001751725,0.0003102228,0.0001998095,0.0004068565,0.0004720902],"domain_scores_gemma":[0.9992052,0.000007862955,0.000008233679,0.0002019973,0.0005171957,0.00005955351],"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":[0.000002721349,0.000009132412,0.00003449787,0.0001307384,0.0001310482,0.00001295824,0.0006759111,0.8891112,0.1096553,0.0000135555,0.0001360369,0.00008684739],"study_design_scores_gemma":[0.0000866625,0.000006964885,8.92354e-7,0.0000188082,0.00003202278,0.000008266576,0.0001454522,0.6321496,0.3654442,0.00005435284,0.001981737,0.00007098871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5410457,0.0005121172,0.4572406,0.0002193987,0.0002344872,0.0002043482,0.00002121013,0.0001489004,0.0003733342],"genre_scores_gemma":[0.9963377,0.00002306691,0.00226948,0.000001356779,0.0001476239,0.00001542532,0.0003285782,0.00003579962,0.0008410195],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.455292,"threshold_uncertainty_score":0.3019919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1052345638775606,"score_gpt":0.3119710013254625,"score_spread":0.2067364374479019,"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."}}