{"id":"W3040780676","doi":"10.1109/mvt.2020.3002522","title":"Detecting Fake Mobile Crowdsensing Tasks: Ensemble Methods Under Limited Data","year":2020,"lang":"en","type":"article","venue":"IEEE Vehicular Technology Magazine","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Istanbul Teknik Üniversitesi","keywords":"Boosting (machine learning); Computer science; AdaBoost; Leverage (statistics); Machine learning; Ensemble learning; Crowdsensing; Mobile device; Artificial intelligence; Classifier (UML); Data science; World Wide Web","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001081958,0.0004730938,0.0006346446,0.0004629723,0.0004532539,0.0003054873,0.002696319,0.0005462285,0.00001046558],"category_scores_gemma":[0.0006805742,0.0004774051,0.0001274519,0.002752943,0.0002781887,0.0005566964,0.00164925,0.001044489,0.0002759596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006855946,"about_ca_system_score_gemma":0.0001153055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001209748,"about_ca_topic_score_gemma":0.00001409455,"domain_scores_codex":[0.9960783,0.00030704,0.0006484448,0.001692599,0.0003676376,0.0009059741],"domain_scores_gemma":[0.9956524,0.000287225,0.0002892534,0.003295664,0.0002325601,0.0002428847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009108368,0.00005159649,0.00008288633,0.00004121881,0.00009640445,0.0002840184,0.0002153103,0.005557253,0.7289131,0.0008208461,0.001554099,0.2623742],"study_design_scores_gemma":[0.0006826824,0.0002484698,0.00005764126,0.00008886968,0.00007324693,0.0005519973,0.0002355796,0.5992395,0.3585564,0.001531216,0.03801746,0.0007168892],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1557547,0.001081898,0.833905,0.005424401,0.0005086537,0.0003553519,0.000005511549,0.002629674,0.0003348917],"genre_scores_gemma":[0.6612846,0.00002704753,0.3369257,0.001446257,0.0001685609,0.00001780179,0.00001310761,0.00005751866,0.00005939781],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5936822,"threshold_uncertainty_score":0.9997678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04844445269404901,"score_gpt":0.3109390353760782,"score_spread":0.2624945826820292,"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."}}