{"id":"W7055547716","doi":"","title":"Classification of high-dimensional mislabelled data and online algorithms for high-dimensional streaming data","year":2023,"lang":"en","type":"dissertation","venue":"White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York)","topic":"Particle accelerators and beam dynamics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Resampling; Naive Bayes classifier; Boosting (machine learning); Classifier (UML); Big data; Raw data; Random forest; Probabilistic classification","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005842987,0.001283431,0.001662311,0.001417233,0.0008005499,0.002497565,0.00364624,0.002544399,0.00247131],"category_scores_gemma":[0.02897267,0.0008711051,0.001421442,0.001812997,0.001668426,0.004347721,0.002538192,0.004479479,0.001843214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001165238,"about_ca_system_score_gemma":0.001254615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002031247,"about_ca_topic_score_gemma":0.002820272,"domain_scores_codex":[0.9969759,0.00134287,0.0001984179,0.0007533901,0.000568674,0.0001608392],"domain_scores_gemma":[0.978024,0.01578671,0.001302403,0.002965614,0.001579735,0.0003414722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002779691,0.0002728528,0.007815048,0.0005586931,0.0002054737,0.0003109504,0.0008646718,0.3840921,0.006007437,0.08714177,0.01247845,0.4999745],"study_design_scores_gemma":[0.000008495816,0.00003075163,0.0004499824,0.00002866556,0.00001042216,0.00005391319,0.00004883893,0.9514915,0.0009335377,0.04529266,0.001635313,0.00001590826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004673331,0.0004401885,0.9933335,0.0004477362,0.00006278416,0.00003959989,0.00006910896,0.0005335183,0.0004002122],"genre_scores_gemma":[0.1411142,0.0008667565,0.8523368,0.0005514786,0.0005537191,0.0003256052,0.0008410768,0.0003673079,0.003043013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005842987,"threshold_uncertainty_score":0.03090101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04911985562435892,"score_gpt":0.2483522832664876,"score_spread":0.1992324276421287,"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."}}