{"id":"W4376564152","doi":"10.1111/tgis.13057","title":"Trailer allocation and truck routing using bipartite graph assignment and deep reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Transactions in GIS","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Northern Digital (Canada); National Research Council Canada; University of Calgary","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Truck; Bipartite graph; Trailer; Computer science; Routing (electronic design automation); Heuristics; Vehicle routing problem; Graph; Mathematical optimization; Transport engineering; Operations research; Engineering; Computer network; Mathematics; Automotive engineering; Theoretical computer 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":[0.000402231,0.0001076852,0.0001152165,0.0002578609,0.0001442495,0.00004197002,0.00003076571,0.00006310814,0.00004991852],"category_scores_gemma":[0.0000169239,0.000127547,0.00002096948,0.0005504606,0.00002773992,0.0001643322,0.000004332522,0.0001784163,0.000002919859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007093771,"about_ca_system_score_gemma":0.000006873402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003556032,"about_ca_topic_score_gemma":0.00002445104,"domain_scores_codex":[0.9992353,0.00005659207,0.0002428046,0.0001530925,0.0001074124,0.0002047512],"domain_scores_gemma":[0.9997535,0.00007591189,0.00002590675,0.00008165522,0.00001395677,0.00004910238],"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":[0.000002156811,0.000003257022,0.001297479,0.00003084354,0.00001657803,9.129123e-7,0.001716365,0.9711698,0.003742076,0.00003623604,9.498521e-7,0.02198338],"study_design_scores_gemma":[0.0003035272,0.00001260027,0.004664351,0.00004861103,0.00002055757,0.000005075338,0.0005054064,0.9929791,0.001193791,0.00002975252,0.0001064708,0.0001307586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2239241,0.00006230826,0.775335,0.00004552756,0.00008467981,0.0001138749,4.450115e-7,0.0002562526,0.0001778374],"genre_scores_gemma":[0.9780343,0.0003290034,0.02146321,0.000008349105,0.0000138408,0.00002131962,0.000004679297,0.00002828038,0.00009705455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7541102,"threshold_uncertainty_score":0.5201217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02720644998993988,"score_gpt":0.2731889428976228,"score_spread":0.2459824929076829,"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."}}