{"id":"W7117476694","doi":"10.1016/j.elerap.2025.101571","title":"A reinforcement learning-driven framework for the Q-commerce multi-product unit scheduling problem","year":2025,"lang":"en","type":"article","venue":"Electronic Commerce Research and Applications","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Laurentian University","funders":"Humanities and Social Science Fund of Ministry of Education of China; State Key Laboratory of Fluid Power and Mechatronic Systems; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Job shop scheduling; Scheduling (production processes); Variable neighborhood search; Reinforcement learning; Metaheuristic; Workload; Dynamic priority scheduling; Fair-share scheduling","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":[],"consensus_categories":[],"category_scores_codex":[0.0007252488,0.0001402751,0.0001355448,0.0001559174,0.001050271,0.0001336251,0.0003691294,0.00007532383,0.00002055845],"category_scores_gemma":[0.0001395589,0.0001203132,0.00004399575,0.0009160028,0.0001251224,0.0000526264,0.00009654893,0.001097855,0.00001523962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140643,"about_ca_system_score_gemma":0.000128318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002361436,"about_ca_topic_score_gemma":0.00002381274,"domain_scores_codex":[0.9986349,0.00005502383,0.0002182928,0.0002667949,0.0001763542,0.0006485839],"domain_scores_gemma":[0.9983459,0.0009286911,0.00002435462,0.0004213489,0.0001961794,0.00008351135],"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":[0.00002063485,0.00007794426,0.0003300643,0.0001408119,0.000167052,7.230374e-8,0.0002547685,0.6700566,0.000314585,0.2557465,0.0004632287,0.0724277],"study_design_scores_gemma":[0.0004252481,0.00006913483,0.0001608472,0.00005974537,0.00002263238,0.000001257543,0.0006308374,0.8612199,0.0004383394,0.005964306,0.1308584,0.0001493171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005490067,0.004438262,0.987547,0.004826812,0.0000252328,0.001462467,0.000002729398,0.0002202139,0.0009282644],"genre_scores_gemma":[0.8432263,0.006719,0.1389928,0.0002219757,0.0002760958,0.005738511,0.00009563218,0.00006981801,0.00465989],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8485543,"threshold_uncertainty_score":0.807794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04489443385723534,"score_gpt":0.3579772916523766,"score_spread":0.3130828577951412,"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."}}