{"id":"W4384026624","doi":"10.1109/icbc56567.2023.10174907","title":"Towards Improved Illicit Node Detection with Positive-Unlabelled Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Database transaction; Task (project management); Graph; Random forest; Node (physics); Feature learning; Representation (politics); Feature (linguistics); Data mining; Pattern recognition (psychology); Theoretical computer science","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":[0.0002601654,0.0001164518,0.0001103823,0.0001768848,0.0001804395,0.000143841,0.000489414,0.00005675979,0.00001456302],"category_scores_gemma":[0.00005880628,0.00009326865,0.00002567735,0.001050625,0.00003096286,0.00051093,0.0001946208,0.00016913,0.000193996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000586477,"about_ca_system_score_gemma":0.00004404178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009568944,"about_ca_topic_score_gemma":0.00001799664,"domain_scores_codex":[0.9989601,0.00005418996,0.0001451427,0.0003823135,0.0002060468,0.0002521635],"domain_scores_gemma":[0.9992341,0.00005011803,0.00007801344,0.0004542432,0.0001284088,0.00005510529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003054808,0.00004350046,0.0004633994,0.00001648629,0.00003467584,0.00001378504,0.0005650124,0.0001176521,0.6171637,0.0174138,0.001051071,0.3630864],"study_design_scores_gemma":[0.0003662663,0.0002561522,0.01304325,0.00001653755,0.000004744705,0.00001575452,0.00006420074,0.378385,0.6010284,0.0005922486,0.005948532,0.0002788993],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008612464,0.000003128755,0.9797828,0.0008200044,0.00006661975,0.0001882254,0.000001999369,0.003210598,0.007314208],"genre_scores_gemma":[0.888656,0.00001941919,0.1070026,0.0002956531,0.00003009054,0.00007611647,0.00002303098,0.00001809624,0.003879097],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8800435,"threshold_uncertainty_score":0.3803385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0121302752733652,"score_gpt":0.2432536760720499,"score_spread":0.2311234007986847,"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."}}