{"id":"W3204221696","doi":"10.1016/j.orl.2022.01.018","title":"Guidelines for the computational testing of machine learning approaches to vehicle routing problems","year":2022,"lang":"en","type":"article","venue":"Operations Research Letters","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Heuristics; Vehicle routing problem; Computer science; Routing (electronic design automation); Work (physics); Machine learning; Management science; Operations research; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03480418,0.002822252,0.001882654,0.005065145,0.00211676,0.005473327,0.009508629,0.006287485,0.01630721],"category_scores_gemma":[0.2234211,0.001911588,0.002428315,0.00377649,0.003831315,0.004876628,0.004796619,0.009947669,0.009663689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001815371,"about_ca_system_score_gemma":0.0059181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006499689,"about_ca_topic_score_gemma":0.009153382,"domain_scores_codex":[0.9475619,0.03334121,0.00648848,0.001441895,0.01031117,0.0008554549],"domain_scores_gemma":[0.792034,0.1367974,0.004797647,0.02322484,0.04151158,0.001634523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003188351,0.001203442,0.002379977,0.002140524,0.0001787221,0.0009495362,0.0009797759,0.07924627,0.004850587,0.4796658,0.1423511,0.2857355],"study_design_scores_gemma":[0.000492034,0.0003962319,0.001147414,0.003254214,0.00008609419,0.0005663827,0.0005380748,0.2800239,0.009020852,0.5577521,0.1465221,0.0002006506],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002424718,0.001783968,0.9670528,0.005590382,0.0005682458,0.001390713,0.001272304,0.002397877,0.0175191],"genre_scores_gemma":[0.01718924,0.0009078035,0.9716532,0.001283402,0.0002710884,0.002974029,0.001366715,0.0009976702,0.003357046],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03480418,"threshold_uncertainty_score":0.1840643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3807223978616506,"score_gpt":0.3906359972719764,"score_spread":0.009913599410325769,"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."}}