{"id":"W2798768357","doi":"10.48550/arxiv.1805.00904","title":"SynTF: Synthetic and Differentially Private Term Frequency Vectors for Privacy-Preserving Text Mining","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Term (time); Computer science; Internet privacy; Computer security; Data mining; Business; Physics","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"],"consensus_categories":[],"category_scores_codex":[0.0002771151,0.0003660099,0.0003551788,0.0003039742,0.0003489655,0.0003831854,0.002245246,0.0003249909,0.00002379228],"category_scores_gemma":[0.0002083346,0.0004100691,0.0001800966,0.0002982954,0.000131886,0.0004855518,0.003212791,0.0003308094,0.00001318284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001444971,"about_ca_system_score_gemma":0.00010624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001066968,"about_ca_topic_score_gemma":0.00004091314,"domain_scores_codex":[0.9977954,0.0001216961,0.0002305984,0.001321857,0.0001043456,0.0004261142],"domain_scores_gemma":[0.9977058,0.0002631578,0.0002996138,0.001418258,0.0001363697,0.0001768],"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":[0.0009868373,0.001559107,0.3588541,0.00848332,0.003760115,0.001176046,0.02433027,0.01795976,0.0379716,0.4711416,0.003127819,0.07064936],"study_design_scores_gemma":[0.001608454,0.0005832419,0.0588981,0.00158471,0.0004614923,0.00003342915,0.00007889362,0.64007,0.004313864,0.2893373,0.0007773547,0.002253206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6276085,0.00004453414,0.3704684,0.0000586614,0.0009465407,0.0003104486,0.000008603095,0.0002097598,0.000344592],"genre_scores_gemma":[0.9919693,0.00006588777,0.007385595,0.00002934883,0.0002016992,0.000003962892,0.000008068134,0.00003127169,0.0003048955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6221102,"threshold_uncertainty_score":0.9998351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05674375505681608,"score_gpt":0.1929583039478873,"score_spread":0.1362145488910713,"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."}}