{"id":"W2769284531","doi":"10.1016/j.eswa.2017.11.039","title":"A hybrid machine-learning and optimization method to solve bi-level problems","year":2017,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":63,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Solver; Mathematical optimization; MATLAB; Optimization problem; Set (abstract data type); Nonlinear system; Integer (computer science); Integer programming; Nonlinear programming; Artificial intelligence; Machine learning; Algorithm; Mathematics","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":[0.0004319503,0.0001129771,0.0001472431,0.0000857378,0.002369091,0.000406897,0.0002014765,0.00005520829,0.00001778828],"category_scores_gemma":[0.00005519314,0.0001019002,0.00001835099,0.0001174674,0.00008165051,0.0002623711,0.00001446352,0.00008624035,0.00001390372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003881871,"about_ca_system_score_gemma":0.00006317735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005598871,"about_ca_topic_score_gemma":0.0005218685,"domain_scores_codex":[0.9989794,0.00007106455,0.0001986689,0.0003084764,0.000246136,0.0001962834],"domain_scores_gemma":[0.9991034,0.00007148577,0.0002197514,0.0002430393,0.0001854657,0.0001768583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004277438,0.0001075567,0.01357133,0.00007560119,0.00007932812,0.00000334219,0.04488957,0.8657057,0.0003140768,0.0623443,0.001493442,0.011373],"study_design_scores_gemma":[0.0009427879,0.000107015,0.002481482,0.0002492131,0.00004819281,0.00001609861,0.005489808,0.1843713,0.0001215566,0.0001379474,0.805334,0.0007005886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000153436,0.000268942,0.99181,0.001350441,0.0000576049,0.001114442,0.00003283634,0.0001691995,0.005043113],"genre_scores_gemma":[0.4127898,0.0001926554,0.5806983,0.0001170915,0.000278346,0.002288736,0.0001660297,0.00004058168,0.003428507],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8038405,"threshold_uncertainty_score":0.9989297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0343912978799911,"score_gpt":0.3337380136444488,"score_spread":0.2993467157644576,"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."}}