{"id":"W4413270905","doi":"10.1016/j.trc.2025.105278","title":"Generating practical last-mile delivery routes using a data-informed insertion heuristic","year":2025,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Urban and Freight Transport Logistics","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Mile; Heuristic; Last mile (transportation); Computer science; Transport engineering; Engineering; Operations research; Geography; Artificial intelligence","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":[0.0005401514,0.0002223697,0.0002541881,0.0005942215,0.0003550006,0.00008887971,0.0005111172,0.000241377,0.00003221733],"category_scores_gemma":[0.0004645862,0.0002259734,0.00004845775,0.001154709,0.0003061067,0.0005225049,0.00003861035,0.000760815,0.0000180609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355545,"about_ca_system_score_gemma":0.00020936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001540717,"about_ca_topic_score_gemma":0.001245244,"domain_scores_codex":[0.9979054,0.00004101327,0.0005700115,0.0003956495,0.0004715094,0.0006164712],"domain_scores_gemma":[0.9986243,0.0003425018,0.00004551048,0.0007056358,0.0002313532,0.00005075854],"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":[0.0004190175,0.0008427653,0.09916895,0.005605105,0.001648262,0.001015712,0.002468442,0.463014,0.1062492,0.1044904,0.1144691,0.100609],"study_design_scores_gemma":[0.000691156,0.00007254685,0.007443239,0.0004439742,0.0001357291,0.000002992672,0.002927773,0.9224917,0.008618281,0.002430659,0.05417274,0.000569204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7059942,0.002106355,0.2824283,0.0009281941,0.0006858851,0.0008353328,0.0003042296,0.005529835,0.001187641],"genre_scores_gemma":[0.9604911,0.001289265,0.03737453,0.00002214601,0.00004588548,0.00007182938,0.0005731386,0.00003459084,0.00009746578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4594777,"threshold_uncertainty_score":0.9214926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1870813155078189,"score_gpt":0.3881737265611778,"score_spread":0.201092411053359,"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."}}