{"id":"W7118992878","doi":"10.1109/vtc2025-fall65116.2025.11310004","title":"Air-Ground Collaborative Mobile Crowdsensing by Predictive Multi-Agent Deep Reinforcement Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Crowdsensing; Trajectory; Reinforcement learning; Visualization; Mobile device; Data collection; Activity recognition; Deep learning","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","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001440118,0.001173648,0.00113325,0.0005720822,0.00272366,0.001736093,0.00113345,0.0005481634,0.0001767115],"category_scores_gemma":[0.0003962153,0.001231626,0.0003813275,0.003229412,0.0006487639,0.00119352,0.001465941,0.0014345,0.0001892178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001224854,"about_ca_system_score_gemma":0.001042975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000509635,"about_ca_topic_score_gemma":0.00008658614,"domain_scores_codex":[0.9920399,0.0009262509,0.001722756,0.002365034,0.001103084,0.001842972],"domain_scores_gemma":[0.9950659,0.0006531642,0.0007357122,0.001561629,0.001442546,0.0005410161],"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":[0.0002080963,0.0006827234,0.0005279278,0.0002640478,0.0009072655,0.000108447,0.02194968,0.847851,0.01189942,0.002867965,0.01299846,0.09973496],"study_design_scores_gemma":[0.002377132,0.0009245707,0.0002946566,0.0007639281,0.0001974006,0.0000201966,0.01098014,0.9241977,0.02098181,0.00005792607,0.03810165,0.001102924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02147814,0.00515207,0.9460817,0.0005603078,0.002880999,0.002158774,0.000007552007,0.0006627843,0.02101769],"genre_scores_gemma":[0.9365973,0.0004347103,0.01150826,0.001373848,0.0001571404,0.0001375969,0.00003331691,0.00006884761,0.04968898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9345734,"threshold_uncertainty_score":0.9993002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00852145869154304,"score_gpt":0.2523099187516344,"score_spread":0.2437884600600914,"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."}}