{"id":"W2853432192","doi":"10.1145/3213846.3213873","title":"Analyzing the analyzers: FlowDroid/IccTA, AmanDroid, and DroidSafe","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Rendering (computer graphics); Benchmark (surveying); Set (abstract data type); Static analysis; Data mining; Artificial intelligence; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0003342759,0.0001340593,0.0001292919,0.0001377378,0.0003485912,0.0002059665,0.0006674369,0.00004814902,0.00006194449],"category_scores_gemma":[0.00005190484,0.00009100445,0.00004902128,0.0006256978,0.0001970713,0.0006311386,0.0003669873,0.000132101,0.00005465392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002996296,"about_ca_system_score_gemma":0.00001854243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004087308,"about_ca_topic_score_gemma":0.00007660229,"domain_scores_codex":[0.9989641,0.00003996756,0.0001892143,0.0003989514,0.000155165,0.0002526102],"domain_scores_gemma":[0.9989556,0.00008150838,0.00006863874,0.0006977071,0.0001171071,0.00007940317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002963393,0.00007648532,0.00543434,0.00002041383,0.000128499,0.00003069011,0.00170428,0.00002773957,0.01507101,0.1920653,0.01632593,0.7690856],"study_design_scores_gemma":[0.001085659,0.001280981,0.01237219,0.00006854211,0.0000599854,0.0004277528,0.0004263187,0.2381883,0.4267377,0.199763,0.1179731,0.001616494],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01235323,0.0001433444,0.9785192,0.001254464,0.0001456279,0.0001313838,4.249736e-7,0.0007412081,0.006711109],"genre_scores_gemma":[0.8754761,0.00005779379,0.1228445,0.0005918533,0.0001441234,0.00001552979,3.117314e-7,0.00000996235,0.0008597989],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8631229,"threshold_uncertainty_score":0.3711054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007593334550513742,"score_gpt":0.2476467336094847,"score_spread":0.2400533990589709,"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."}}