{"id":"W4404424456","doi":"10.2139/ssrn.5021795","title":"Maximizing Information Gain in Privacy-Aware Active Learning of Email Anomalies","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Information gain; Computer science; Internet privacy; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008584093,0.0009284928,0.002534918,0.001613113,0.0007251097,0.002640991,0.002490117,0.002873215,0.001475088],"category_scores_gemma":[0.04895541,0.0008155113,0.0007452428,0.001425363,0.001980269,0.005727284,0.0033153,0.002464176,0.0002544282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001515713,"about_ca_system_score_gemma":0.001834009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001658728,"about_ca_topic_score_gemma":0.001491125,"domain_scores_codex":[0.9953435,0.002171263,0.0002533866,0.0008927192,0.0007950469,0.0005439194],"domain_scores_gemma":[0.924717,0.06738196,0.002691321,0.002495529,0.001721066,0.0009931631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001495664,0.0008410652,0.01137744,0.000258744,0.0002149822,0.0001737759,0.0003422132,0.8036611,0.003530479,0.03357031,0.001687894,0.1428463],"study_design_scores_gemma":[0.00002345702,0.0001116713,0.0006300564,0.00001120979,0.00002450513,0.0000357798,0.00002658128,0.9755473,0.0008727792,0.02262824,0.00007978921,0.000008667213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2857804,0.0008157528,0.7078118,0.001666653,0.00007068503,0.0001321571,0.0001912528,0.0004980908,0.003033112],"genre_scores_gemma":[0.9846052,0.0001420423,0.01419024,0.000080142,0.00008513508,0.00003248261,0.00006334925,0.00002962134,0.0007718519],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008584093,"threshold_uncertainty_score":0.04539758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09276002986324035,"score_gpt":0.3839509198760234,"score_spread":0.291190890012783,"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."}}