{"id":"W4414276449","doi":"10.1287/msom.2024.1317","title":"Machine Learning–Augmented Optimization of Large Bilevel and Two-Stage Stochastic Programs: Application to Cycling Network Design","year":2025,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Bilevel optimization; Representation (politics); Network planning and design; Exploit; Work (physics); Function (biology); Quality (philosophy); Stochastic programming; Decision problem","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006866418,0.0001379573,0.0001458242,0.0002097611,0.0008648655,0.0001506004,0.0001608992,0.00004988805,0.00003599638],"category_scores_gemma":[0.00001856353,0.0001510036,0.00002229233,0.0006058214,0.00002279346,0.0001905971,0.00005101438,0.00009225154,0.00000586164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006908865,"about_ca_system_score_gemma":0.00003375654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001066185,"about_ca_topic_score_gemma":0.002654058,"domain_scores_codex":[0.9987256,0.0001452656,0.0003317614,0.0003134422,0.0002278963,0.0002560219],"domain_scores_gemma":[0.9994945,0.00005457638,0.00008719016,0.0001689135,0.0001255118,0.0000693312],"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":[0.00002620883,0.00007050632,0.0003959397,0.00007327961,0.0000433274,4.667258e-7,0.002137096,0.982402,0.000008976837,0.009024422,0.00001459693,0.005803181],"study_design_scores_gemma":[0.0008536233,0.00003609061,0.00231946,0.0001706487,0.0001086501,8.752272e-8,0.002316845,0.9896178,0.0001190124,0.0001287836,0.004127603,0.0002014381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008591074,0.00005120211,0.9873847,0.001157817,0.00009446437,0.001515713,0.000007668622,0.0001670604,0.001030291],"genre_scores_gemma":[0.8621478,0.00006174197,0.1346548,0.0004780594,0.00003758111,0.0002733644,0.0003221124,0.00001621948,0.002008288],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8535567,"threshold_uncertainty_score":0.6651934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01519567692607715,"score_gpt":0.285990401438279,"score_spread":0.2707947245122019,"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."}}