{"id":"W4220690511","doi":"10.1007/s10664-021-10109-y","title":"Why secret detection tools are not enough: It’s not just about false positives - An industrial case study","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"National Security Agency; North Carolina State University; National Science Foundation","keywords":"False positive paradox; Computer security; Computer science; True positive rate; Data science; Artificial intelligence","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":[0.0005284437,0.0003777533,0.0003796891,0.0003507024,0.0006728069,0.0002974621,0.0007599843,0.0001461957,0.00004245701],"category_scores_gemma":[0.0008043637,0.0004306425,0.0001253548,0.001084244,0.0000255318,0.001335865,0.0008318364,0.001093939,0.000005641688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005036097,"about_ca_system_score_gemma":0.00005562223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001912023,"about_ca_topic_score_gemma":0.00006049818,"domain_scores_codex":[0.9971676,0.0002500678,0.0004925961,0.000886214,0.0006711798,0.0005323357],"domain_scores_gemma":[0.9981937,0.0004884761,0.0001777917,0.0007604521,0.0001138779,0.0002656318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008076903,0.005001349,0.02132387,0.0002127243,0.0005886893,0.04092084,0.04001746,0.4230561,0.01866353,0.0002643226,0.007480518,0.4416629],"study_design_scores_gemma":[0.01186635,0.02011757,0.07237997,0.0003146056,0.0003877214,0.03027228,0.02386967,0.1988622,0.2818412,0.0003340313,0.3483109,0.01144356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3972232,0.00001359759,0.5990293,0.0003204612,0.0007152741,0.0004874711,0.00003160465,0.002176764,0.000002264725],"genre_scores_gemma":[0.9803837,0.000001437663,0.01719886,0.001538216,0.0003308848,0.0004490493,0.000007431146,0.00006049938,0.00002991756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5831605,"threshold_uncertainty_score":0.9998145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08079733134382909,"score_gpt":0.315110970198614,"score_spread":0.2343136388547849,"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."}}