{"id":"W4368755397","doi":"10.48550/arxiv.2305.02112","title":"Heterogeneous GNN-RL Based Task Offloading for UAV-aided Smart Agriculture","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Computer science; Reinforcement learning; Internet of Things; Robustness (evolution); Edge computing; Task (project management); Network topology; Distributed computing; Enhanced Data Rates for GSM Evolution; Real-time computing; Embedded system; Computer network; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003068808,0.0005797272,0.0004576751,0.0001942165,0.0003212601,0.0003933189,0.0007582826,0.0004921716,0.001295587],"category_scores_gemma":[0.0006485034,0.0001642907,0.0002104727,0.0001800855,0.0003808189,0.0004874121,0.0006142181,0.0005425603,0.0001992378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005365206,"about_ca_system_score_gemma":0.0006061343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005939819,"about_ca_topic_score_gemma":0.008280803,"domain_scores_codex":[0.9998595,0.00002326808,0.000005076818,0.00004073089,0.00002582365,0.00004556982],"domain_scores_gemma":[0.9997705,0.00009195219,0.00003364067,0.00002355347,0.00005064444,0.00002974265],"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":[0.0001217303,0.00008335365,0.000582227,0.00002856861,0.00001799104,0.00007936158,0.00002885062,0.9597957,0.006251927,0.001184122,0.0009329902,0.03089333],"study_design_scores_gemma":[0.000005059482,0.00001556833,0.00008656918,0.000001423121,0.000002310921,0.000004444602,0.00000513708,0.9987572,0.0004399444,0.0005374604,0.0001432442,0.000001682155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1478051,0.0004505358,0.841624,0.0003157569,0.0001742833,0.00007323111,0.00007570386,0.0009573425,0.008524002],"genre_scores_gemma":[0.9805684,0.00004462111,0.01766743,0.00007289834,0.00001321105,0.00002693746,0.00004153325,0.00002817467,0.001536783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005939819,"threshold_uncertainty_score":0.01181048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09812038311716764,"score_gpt":0.1900401904746339,"score_spread":0.09191980735746624,"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."}}