{"id":"W4400532948","doi":"10.1016/j.tust.2024.105958","title":"A hybrid machine learning-based model for predicting failure of water mains under climatic variations: A Hong Kong case study","year":2024,"lang":"en","type":"article","venue":"Tunnelling and Underground Space Technology","topic":"Water Systems and Optimization","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Mains electricity; Engineering; Forensic engineering; Machine learning; Mechanical engineering; Environmental science; Computer science; Electrical engineering","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":[0.0002887585,0.0001951079,0.0002699046,0.0004201166,0.0001852341,0.00009609352,0.00007398797,0.0001402485,0.000003546767],"category_scores_gemma":[0.00001718054,0.0001616573,0.00004935374,0.0001815468,0.00003965119,0.0001230275,0.00003106289,0.0002620578,0.000001560029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005992987,"about_ca_system_score_gemma":0.00001708974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000100529,"about_ca_topic_score_gemma":0.00100571,"domain_scores_codex":[0.9990124,0.00002531617,0.0003268489,0.0002679371,0.00008398652,0.0002835466],"domain_scores_gemma":[0.9995934,0.0001019268,0.00003872875,0.0001823582,0.00004772357,0.00003580333],"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":[0.000004964197,0.00004043452,0.0005307099,0.0005176254,0.000121542,0.00007461552,0.001349801,0.9947149,0.0003668776,0.002178796,0.00002646678,0.00007324936],"study_design_scores_gemma":[0.0005016195,0.0001523158,0.000001696045,0.0001294454,0.0001211447,0.000298652,0.002845159,0.9907601,0.000460107,0.004519034,0.00003448548,0.0001762744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3638317,0.0003657713,0.6343545,0.0003189238,0.00008709436,0.0003375589,0.000009393834,0.0006810807,0.00001393681],"genre_scores_gemma":[0.9938203,0.00002210035,0.005710019,0.000004526999,0.00003269659,0.00006868918,0.00002610678,0.00006746335,0.0002481733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6299886,"threshold_uncertainty_score":0.6592191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01237543794578744,"score_gpt":0.2202846426509441,"score_spread":0.2079092047051566,"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."}}