{"id":"W2547900581","doi":"10.1145/2950290.2950348","title":"Detecting sensitive data disclosure via bi-directional text correlation analysis","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Cisco Systems; National Science Foundation","keywords":"Citation; Computer science; Information retrieval; Library science; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003616205,0.0001362303,0.0001624324,0.0003592159,0.0001882245,0.00006366098,0.0005827103,0.00007253465,0.00006503765],"category_scores_gemma":[0.0002180399,0.00009468844,0.00007662844,0.00142664,0.00004321809,0.001652576,0.0005331832,0.00009982861,0.00007693544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009675336,"about_ca_system_score_gemma":0.00002611398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005749434,"about_ca_topic_score_gemma":0.0002156251,"domain_scores_codex":[0.998521,0.00008730742,0.0002388896,0.0006636404,0.0002856431,0.0002034797],"domain_scores_gemma":[0.9982139,0.0003012423,0.0001489512,0.001091791,0.000175633,0.00006843994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001664338,0.00004425047,0.004579978,0.000003239916,0.0003173391,0.00001280679,0.0001274477,0.0004865367,0.03233426,0.003773365,0.0005781068,0.957726],"study_design_scores_gemma":[0.0004889033,0.0001677252,0.03367431,0.00004014364,0.0002206402,0.000141519,0.00006829607,0.6698793,0.2755491,0.01332473,0.005546052,0.0008992176],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001286575,0.000008524759,0.9952145,0.0005887517,0.0002178593,0.0001076753,0.00001388282,0.001228942,0.001333319],"genre_scores_gemma":[0.7938312,0.00000450276,0.2050946,0.00008000447,0.00006380527,0.000007900162,0.000008457466,0.000007880987,0.0009015995],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9568268,"threshold_uncertainty_score":0.3861282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01876336455985773,"score_gpt":0.2709647398160218,"score_spread":0.252201375256164,"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."}}