{"id":"W3140856702","doi":"10.1287/trsc.2021.1084","title":"An Improved Integral Column Generation Algorithm Using Machine Learning for Aircrew Pairing","year":2021,"lang":"en","type":"article","venue":"Transportation Science","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"Pairing; Crew; Aircrew; Column generation; Computer science; Algorithm; Scheduling (production processes); Crew scheduling; Process (computing); Set (abstract data type); Engineering; Mathematics; Mathematical optimization; Aeronautics; Physics; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0007819238,0.0001120469,0.0001246995,0.0001082821,0.0003195333,0.0001366596,0.0001299319,0.00004810312,0.00002797831],"category_scores_gemma":[0.00007841695,0.0001325138,0.0000411641,0.0007656595,0.00006243796,0.0007005381,0.000002324487,0.000126461,8.909556e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008790972,"about_ca_system_score_gemma":0.0001283602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004184289,"about_ca_topic_score_gemma":0.0001365047,"domain_scores_codex":[0.9989173,0.00003840842,0.0002800612,0.0002987867,0.000215833,0.0002495441],"domain_scores_gemma":[0.9993429,0.00003627399,0.00004993106,0.0001474519,0.0003252582,0.000098181],"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":[8.401138e-7,0.000006637234,0.000811313,0.00001246853,0.000002742765,0.000001004124,0.0003953834,0.5950562,0.3786062,0.0000448355,5.608459e-7,0.02506177],"study_design_scores_gemma":[0.0002265671,0.00002163747,0.00169137,0.00001010716,0.00001333463,0.000002493637,0.0001171653,0.8480581,0.1496235,0.00001369797,0.00008599064,0.0001360287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2814305,0.00004302305,0.7179279,0.00001026171,0.0002312869,0.0001145494,0.00001257095,0.0002125959,0.00001731508],"genre_scores_gemma":[0.4962349,0.000006552766,0.5035308,0.0000209239,0.00005418179,0.000009852578,0.0000995647,0.00001863171,0.00002455503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2530018,"threshold_uncertainty_score":0.5403755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03862218519718917,"score_gpt":0.3131411882160839,"score_spread":0.2745190030188947,"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."}}