{"id":"W4409791323","doi":"10.61091/jcmcc127a-400","title":"Deep reinforcement learning-based heterogeneous graph neural networks for multi-task financial fraud detection: a new framework incorporating variational self-encoders","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Computer science; Encoder; Task (project management); Artificial intelligence; Graph; Artificial neural network; Machine learning; Theoretical computer science; Management","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001508976,0.0003660195,0.0006702509,0.0003913762,0.0007014597,0.0005690509,0.0009688158,0.0003331905,0.000001110391],"category_scores_gemma":[0.001470069,0.0003685743,0.0002646364,0.0007955604,0.00006130295,0.000409224,0.0003000593,0.0008292134,3.534663e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002101237,"about_ca_system_score_gemma":0.0004963848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006591699,"about_ca_topic_score_gemma":8.751264e-7,"domain_scores_codex":[0.9969766,0.0001632856,0.001455914,0.0003957138,0.0005930792,0.0004153982],"domain_scores_gemma":[0.9957847,0.001065567,0.001848548,0.000404911,0.000697344,0.0001989523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000134644,0.0004905681,0.00009749186,0.0001728661,0.0001455419,0.000009966915,0.0005938976,0.186353,0.0001020519,0.8048564,0.0001942867,0.006849302],"study_design_scores_gemma":[0.002478457,0.0005794948,0.00002719249,0.0001816231,0.00005310744,0.00001693303,0.00001886068,0.7168055,0.0005533738,0.2787768,0.0002756804,0.0002329724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001505996,0.0001593834,0.9869103,0.0002703971,0.01036771,0.0005621215,5.171308e-7,0.0002047662,0.00001879322],"genre_scores_gemma":[0.7070073,0.00000756825,0.2920541,0.0001306799,0.0007600184,0.00001324188,0.000004276836,0.00001961876,0.000003210297],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7055013,"threshold_uncertainty_score":0.9998766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01411836066600482,"score_gpt":0.2610091801802655,"score_spread":0.2468908195142607,"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."}}