{"id":"W4414603255","doi":"10.1109/jiot.2025.3615410","title":"LLM-Enabled In-Context Learning for Data Collection Scheduling in UAV-Assisted Sensor Networks","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Energy Efficient Wireless Sensor Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Scheduling (production processes); Reinforcement learning; Wireless sensor network; Data collection; Schedule; Network packet; Drone; Task analysis","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":[0.002008999,0.0002129106,0.0004444435,0.0007590583,0.0001256904,0.000342129,0.001846922,0.0002002991,0.000006914482],"category_scores_gemma":[0.0004463718,0.0002145053,0.000114564,0.001056685,0.00004966089,0.0009243191,0.0003791817,0.001192089,0.000001485949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002753129,"about_ca_system_score_gemma":0.0001506338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002607543,"about_ca_topic_score_gemma":0.0002767181,"domain_scores_codex":[0.9974762,0.0002662257,0.0009513503,0.0005138429,0.0002802134,0.0005122263],"domain_scores_gemma":[0.9980425,0.000609866,0.0005547198,0.0004835557,0.0002350355,0.00007429026],"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":[0.0001851267,0.0001736725,0.003995504,0.00003248203,0.00006925495,0.00005266742,0.00126244,0.9555126,0.001194998,0.0005821097,0.0009148205,0.03602426],"study_design_scores_gemma":[0.001516474,0.0001175737,0.0006204832,0.001135898,0.00001261493,0.0001009143,0.0002146673,0.9933074,0.001922405,0.0001503297,0.0007235162,0.0001777906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2656185,0.0003593657,0.7309515,0.0004215392,0.002067049,0.0001551303,1.771575e-7,0.00003572536,0.0003910463],"genre_scores_gemma":[0.9403759,0.00007070643,0.05780754,0.0002332864,0.0001310417,0.000007151058,0.000004002383,0.00001773177,0.00135263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6747574,"threshold_uncertainty_score":0.8747272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02471682922518389,"score_gpt":0.2761115936959591,"score_spread":0.2513947644707752,"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."}}