{"id":"W4313350174","doi":"10.1016/j.orl.2022.12.006","title":"Gradient boosting for convex cone predict and optimize problems","year":2022,"lang":"en","type":"article","venue":"Operations Research Letters","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick; University of Toronto","funders":"","keywords":"Regret; Gradient boosting; Convex optimization; Mathematical optimization; Boosting (machine learning); Regular polygon; Computer science; Quadratic programming; Quadratic equation; Artificial intelligence; Mathematics; Machine learning; Random forest","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01077246,0.0001316682,0.0002449488,0.0007812734,0.003423869,0.0008235333,0.0008909745,0.00003078391,0.0007583722],"category_scores_gemma":[0.006502343,0.0001114773,0.0000667549,0.001392341,0.0005774341,0.0005183943,0.0009083392,0.0007133725,0.00004460297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002506377,"about_ca_system_score_gemma":0.0002217729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001114533,"about_ca_topic_score_gemma":0.00005380099,"domain_scores_codex":[0.9936216,0.0009906302,0.000527558,0.0007843917,0.003284757,0.0007910975],"domain_scores_gemma":[0.9948825,0.003393878,0.00004071691,0.0005994947,0.0008312993,0.0002521029],"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":[0.0001276486,0.0001535444,0.0005908634,0.00001922732,0.00004660366,0.00003597159,0.002162936,0.8696664,0.02109328,0.001418381,0.08909677,0.0155884],"study_design_scores_gemma":[0.001693154,0.0005765675,0.0004564814,0.00001197463,0.000004486992,0.00004566207,0.003233446,0.8452106,0.0007473399,0.001691688,0.1460843,0.0002443167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4176125,0.0008352206,0.4676271,0.1033834,0.0006923301,0.007876932,0.0008196339,0.000143315,0.001009563],"genre_scores_gemma":[0.9490845,0.00006940458,0.03283025,0.001415388,0.0003467971,0.005919631,0.0001299021,0.00006789079,0.01013627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.531472,"threshold_uncertainty_score":0.9978735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2601772201591964,"score_gpt":0.4724558772527916,"score_spread":0.2122786570935952,"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."}}