{"id":"W2734645630","doi":"10.1162/evco_a_00215","title":"Leveraging TSP Solver Complementarity through Machine Learning","year":2017,"lang":"en","type":"article","venue":"Evolutionary Computation","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":92,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutscher Akademischer Austauschdienst","keywords":"Solver; Leverage (statistics); Computer science; Benchmark (surveying); Complementarity (molecular biology); Euclidean geometry; Mathematical optimization; Problem solver; Set (abstract data type); Travelling salesman problem; Parallel computing; Algorithm; Artificial intelligence; Mathematics; Computational science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002736202,0.0001485462,0.0001447394,0.0000558317,0.001009395,0.0001176625,0.0001912784,0.00005257606,0.0001343378],"category_scores_gemma":[0.00008118964,0.000179879,0.00005175093,0.00006952928,0.00005327137,0.0005808237,0.00009442567,0.0002542417,0.00005965211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001897582,"about_ca_system_score_gemma":0.00001916509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001552254,"about_ca_topic_score_gemma":0.000008511499,"domain_scores_codex":[0.9990171,0.00009154728,0.0002470108,0.0002000908,0.0002172496,0.0002270133],"domain_scores_gemma":[0.9994721,0.00008306417,0.000108982,0.0002132435,0.00007939268,0.00004323333],"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":[0.000004081627,0.00001398674,0.02457686,0.00002169858,0.00002732128,0.000002638124,0.000427149,0.9683162,0.0001848883,0.0004439739,0.00124448,0.004736722],"study_design_scores_gemma":[0.0004091258,0.00001388782,0.09565871,0.00001912557,0.00001106046,0.00000911915,0.00004088405,0.8980545,0.00008860525,0.001871277,0.003646735,0.0001770157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05455368,0.0002084068,0.9364676,0.0002860448,0.0006336697,0.0001417222,0.000007888912,0.0006010088,0.007099938],"genre_scores_gemma":[0.7643672,0.00001814671,0.2351784,0.00003861032,0.0001226409,0.000005624232,0.0001436789,0.00002701178,0.0000986774],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7098135,"threshold_uncertainty_score":0.7763554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04305681618019019,"score_gpt":0.305783714799549,"score_spread":0.2627268986193588,"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."}}