{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003990556,0.00008800356,0.0001100209,0.000195692,0.00140151,0.0001041064,0.0002987767,0.00001606021,0.00003369728],"category_scores_gemma":[0.002460388,0.00007897461,0.00003736222,0.001007324,0.00004796357,0.00008754252,0.0001765456,0.0004175165,0.000002834329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001151173,"about_ca_system_score_gemma":0.00005227229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001277044,"about_ca_topic_score_gemma":0.00001515183,"domain_scores_codex":[0.9983147,0.0003582098,0.0003557861,0.0001798061,0.0004955992,0.0002958495],"domain_scores_gemma":[0.9980093,0.001379225,0.00001941779,0.000165439,0.0003794681,0.00004717313],"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":[0.000003365441,0.00001079106,0.0006260025,0.00002288644,0.00002257576,2.295959e-7,0.0007935879,0.9815492,0.01018926,0.0004585811,0.0009454181,0.005378068],"study_design_scores_gemma":[0.0001752422,0.00004565846,0.0001515444,0.00001224393,0.000004432179,0.000002946718,0.0004449775,0.9963211,0.0004480361,0.00001841297,0.002291061,0.00008435851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07793654,0.0001239726,0.9038987,0.01661618,0.00008239972,0.001010269,0.00003680761,0.0001371703,0.0001579189],"genre_scores_gemma":[0.6022679,0.000001554449,0.3966491,0.000250766,0.00008175218,0.0005593747,0.00004219586,0.0000370029,0.000110426],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5243313,"threshold_uncertainty_score":0.9998986,"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."}}