{"id":"W4415233468","doi":"10.48550/arxiv.2507.18242","title":"Boosting Revisited: Benchmarking and Advancing LP-Based Ensemble Methods","year":2025,"lang":"en","type":"preprint","venue":"University of Twente Research Information","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada; TKI DINALOG; Compute Canada","keywords":"Boosting (machine learning); Heuristics; Ensemble learning; Benchmarking; Decision tree; Hyperparameter; Gradient boosting; Margin (machine learning)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01667889,0.002247375,0.002215135,0.002348321,0.0009379082,0.002271857,0.002841835,0.002351651,0.001779442],"category_scores_gemma":[0.03281505,0.0006436663,0.001320871,0.001762252,0.001094985,0.003233952,0.003058663,0.004735994,0.001844736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000913939,"about_ca_system_score_gemma":0.001696851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002940202,"about_ca_topic_score_gemma":0.003197806,"domain_scores_codex":[0.9910443,0.005068678,0.0003459054,0.001102525,0.002073319,0.0003652918],"domain_scores_gemma":[0.9855552,0.006786442,0.0004992447,0.003901447,0.002801662,0.0004561911],"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":[0.0007899347,0.0005232796,0.009450489,0.0005120832,0.0006008858,0.00009962077,0.000237637,0.5654092,0.003398126,0.01411289,0.02382079,0.3810452],"study_design_scores_gemma":[0.00005114459,0.0001702797,0.0006746674,0.00006212883,0.00004209523,0.00004756904,0.00003303444,0.9856725,0.002303819,0.007466021,0.00345864,0.00001813521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1476109,0.009411457,0.8145308,0.001625985,0.001120488,0.0003772099,0.001149538,0.007578454,0.01659523],"genre_scores_gemma":[0.5546972,0.001388986,0.4352075,0.0008697866,0.0005161216,0.0003768923,0.002975406,0.001035307,0.002932788],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01667889,"threshold_uncertainty_score":0.08820742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0482439719890473,"score_gpt":0.3789084719229865,"score_spread":0.3306644999339393,"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."}}