{"id":"W7116869709","doi":"10.1016/j.aei.2025.104263","title":"Co-MixPL: An optimized semi-supervised learning method for tunnel water leakage detection","year":2025,"lang":"en","type":"article","venue":"Advanced Engineering Informatics","topic":"Water Systems and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; National University's Basic Research Foundation of China; National Natural Science Foundation of China","keywords":"Discriminative model; Leakage (economics); Reliability (semiconductor); Regression; Labeled data; Training set","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":[0.0002802084,0.000253013,0.000296246,0.0002447104,0.0001139084,0.00009189353,0.0001412073,0.0001420953,0.00000611498],"category_scores_gemma":[0.00003554166,0.000230677,0.00007863242,0.0001734285,0.000006179079,0.000838847,0.00001665991,0.000219534,0.00001022893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001103584,"about_ca_system_score_gemma":0.000006501479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003334001,"about_ca_topic_score_gemma":0.000004132109,"domain_scores_codex":[0.9988434,0.00001320283,0.0005421811,0.00010805,0.000106017,0.0003871948],"domain_scores_gemma":[0.9995188,0.00006392635,0.00003543879,0.0002307028,0.00007752918,0.00007367619],"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":[0.00001432444,0.000004795923,0.000003408495,0.0005815005,0.00004531973,2.749745e-7,0.001312437,0.972852,0.01783041,0.0000688674,0.00004480612,0.007241882],"study_design_scores_gemma":[0.0009743031,0.00004182772,0.00001205611,0.00007408925,0.00002327707,0.000003405501,0.0002432665,0.8782632,0.1012262,0.0000147866,0.01886778,0.0002557306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01440715,0.00004027914,0.9822478,0.000006613779,0.0007040892,0.00044867,0.000006471967,0.001102472,0.001036404],"genre_scores_gemma":[0.4348344,0.00004043401,0.5638633,0.00003981901,0.00008416384,0.0002459073,0.0002240094,0.00008920756,0.0005788304],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4204272,"threshold_uncertainty_score":0.9406734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005129122955505167,"score_gpt":0.227621807649848,"score_spread":0.2224926846943429,"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."}}