{"id":"W2980984693","doi":"10.1145/3350546.3352550","title":"Detecting Anomalous Behaviour from Textual Content in Financial Records","year":2019,"lang":"en","type":"article","venue":"IEEE/WIC/ACM International Conference on Web Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Anomaly detection; Malpractice; Deep learning; Anomaly (physics); Base (topology); Artificial intelligence; Content (measure theory); Finance; Scale (ratio); Work (physics); Machine learning; Information retrieval; Mathematics; Business; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005125587,0.0003632735,0.0003571153,0.0004479545,0.00008005444,0.0003784072,0.004466897,0.0002188022,0.0007228927],"category_scores_gemma":[0.0007603713,0.0003782798,0.0001128644,0.0004100743,0.0001058843,0.0007426381,0.0005097426,0.0006882218,0.001277718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000399639,"about_ca_system_score_gemma":0.0004069154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001113691,"about_ca_topic_score_gemma":0.0005239586,"domain_scores_codex":[0.9966226,0.0001359772,0.0008390467,0.001136233,0.0007898111,0.0004763158],"domain_scores_gemma":[0.9971305,0.0003747403,0.000396632,0.001441687,0.0005299315,0.0001264836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002725329,0.0007624439,0.1188248,0.00002107944,0.00005793765,0.0001503982,0.001286564,0.0001579102,0.07409491,0.4944085,0.001886596,0.3080764],"study_design_scores_gemma":[0.001453405,0.001425457,0.1470135,0.001387659,0.00002016425,0.00008409245,0.001298508,0.3144733,0.454226,0.0689851,0.006876128,0.002756646],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6723084,0.0000317202,0.3036905,0.002021611,0.004052209,0.0007514561,0.0002310376,0.0005430243,0.01636995],"genre_scores_gemma":[0.9771883,0.00009164848,0.02060851,0.0007884206,0.0001589453,0.0001028891,0.00005119824,0.00002190848,0.000988162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4254234,"threshold_uncertainty_score":0.9998669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09267781734851123,"score_gpt":0.3137047356491844,"score_spread":0.2210269183006732,"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."}}