{"id":"W4417251850","doi":"10.1109/tmc.2025.3642535","title":"Noisy Multi-Label Aggregation With Self-Supervised Graph Transformer in Mobile Crowdsourcing","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Crowdsourcing; Transformer; Graph; Aggregate (composite); Knowledge graph; Noisy data; Labeled data; Data modeling","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":["metaepi_narrow"],"category_scores_codex":[0.001526151,0.001343302,0.001331385,0.002137696,0.002077789,0.001072222,0.001340303,0.0006490684,0.00004718498],"category_scores_gemma":[0.00001076473,0.001409896,0.0005200544,0.005714206,0.0003558051,0.001033801,0.00001795528,0.00227204,0.00006499975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007752551,"about_ca_system_score_gemma":0.0007703311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003893031,"about_ca_topic_score_gemma":0.0004335536,"domain_scores_codex":[0.9918994,0.0006935042,0.001985501,0.002524898,0.0009567002,0.00194],"domain_scores_gemma":[0.9960607,0.0008541758,0.000447627,0.001736268,0.0005018743,0.0003994102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000142488,0.00198856,0.000358655,0.0003900509,0.0002158583,0.00006539941,0.007804887,0.4851727,0.002777398,0.00004097444,0.00001413081,0.5010289],"study_design_scores_gemma":[0.007163473,0.001058127,0.0002731278,0.003957388,0.0002591533,0.00008440916,0.001565154,0.9462652,0.03774242,0.0000331889,0.0002414433,0.001356908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3536718,0.0009234175,0.640492,0.00009448686,0.001715758,0.002153182,0.00001280824,0.0006273683,0.0003091889],"genre_scores_gemma":[0.9345438,0.0003019276,0.06367286,0.0004010132,0.0001052773,0.0003715816,0.000004960784,0.0001284499,0.0004701055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5808721,"threshold_uncertainty_score":0.9999648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01346403791043589,"score_gpt":0.2556648147804227,"score_spread":0.2422007768699868,"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."}}