{"id":"W4360996447","doi":"10.1109/icct56141.2022.10073400","title":"Telecom Fraud Detection via Imbalanced Graph Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Computer science; Graph; Node (physics); Multilayer perceptron; Detector; Data mining; Artificial neural network; Artificial intelligence; Computer network; Telecommunications; Theoretical computer science; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0003470506,0.00009857978,0.0001001797,0.0001876944,0.0005137002,0.000086393,0.0008981136,0.00002902329,0.0001873455],"category_scores_gemma":[0.00002943575,0.0001043611,0.00004754865,0.0008117704,0.00002096383,0.0004126049,0.0004714195,0.0003570781,0.00005140831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000101773,"about_ca_system_score_gemma":0.00002411736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003906146,"about_ca_topic_score_gemma":0.000005729707,"domain_scores_codex":[0.9987634,0.0001385017,0.0001866467,0.0003806351,0.0003059797,0.0002248809],"domain_scores_gemma":[0.9991924,0.00004747197,0.0001107292,0.0005580731,0.00004509553,0.00004626789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001636254,0.0001634366,0.003361674,0.00001105091,0.00002514239,0.00001236843,0.0004542691,0.0008626907,0.3081596,0.0479229,0.005013079,0.6339974],"study_design_scores_gemma":[0.0006457437,0.0006723561,0.01918324,0.000004841791,0.000006941053,0.0001448449,0.0001931025,0.2752728,0.4115364,0.03155514,0.2599265,0.0008580633],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003456635,0.00001967702,0.9900521,0.0004126359,0.0002479562,0.0001391102,0.000001492129,0.001685307,0.00398511],"genre_scores_gemma":[0.9440022,0.000007133254,0.05445495,0.0004219192,0.0000226881,0.0001561831,0.00001231412,0.000009811498,0.0009127608],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9405456,"threshold_uncertainty_score":0.4255723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008522006508991329,"score_gpt":0.2231477434811213,"score_spread":0.2146257369721299,"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."}}