{"id":"W4404657607","doi":"10.2139/ssrn.5031931","title":"Generating Practical Last-Mile Delivery Routes Using a Data-Informed Insertion Heuristic","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Manufacturing and Logistics Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Mile; Last mile (transportation); Heuristic; Computer science; Operations management; Engineering; Artificial intelligence; Geography","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007184796,0.0003634138,0.0003121996,0.0002121896,0.0001892555,0.0003309978,0.0003502369,0.0002814413,0.000009628864],"category_scores_gemma":[0.0003799894,0.0003610063,0.00009091463,0.0001060212,0.00003068374,0.0003006299,0.0005617145,0.005632517,0.00002490264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002118182,"about_ca_system_score_gemma":0.002655977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003919376,"about_ca_topic_score_gemma":0.0003531543,"domain_scores_codex":[0.9972596,0.0000495296,0.0005422162,0.0003702384,0.0002923227,0.001486062],"domain_scores_gemma":[0.9990576,0.0001222489,0.0001781984,0.0004525356,0.00009412406,0.00009532747],"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":[0.00001334487,0.00001489638,0.000005221402,0.0001889509,0.0002530011,0.00002007003,0.00006423568,0.9915075,0.0002411179,0.001555967,0.0001474339,0.005988255],"study_design_scores_gemma":[0.000155576,0.00003688402,0.000004262648,0.0002014335,0.0002321294,0.0004770552,0.000178827,0.9227327,0.0001106732,0.07515489,0.0003572877,0.0003582768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04423625,0.005707821,0.9474728,0.0000829769,0.001664785,0.0001878062,0.00004829515,0.0003907749,0.0002085415],"genre_scores_gemma":[0.9084626,0.01343451,0.07556453,0.00003218518,0.001709118,0.00001141396,0.0004565058,0.0001553036,0.0001738349],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8719082,"threshold_uncertainty_score":0.9998842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03545720047975093,"score_gpt":0.2999455718815768,"score_spread":0.2644883714018259,"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."}}