{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003651845,0.002142243,0.0007896695,0.007351594,0.0008618154,0.001553363,0.001444131,0.0008685108,0.001980719],"category_scores_gemma":[0.01537062,0.000661006,0.000989734,0.002939131,0.0008804321,0.002872204,0.001510183,0.001418877,0.0009544471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001173853,"about_ca_system_score_gemma":0.002466127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004984993,"about_ca_topic_score_gemma":0.005321563,"domain_scores_codex":[0.9943238,0.0009810684,0.0006820945,0.001093614,0.002393167,0.0005263215],"domain_scores_gemma":[0.983648,0.007823022,0.001683149,0.002799696,0.003667902,0.0003782068],"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":[0.002444363,0.0009566465,0.1273398,0.002685818,0.0009362338,0.001110128,0.002243127,0.01865331,0.06480634,0.01187415,0.05730475,0.7096453],"study_design_scores_gemma":[0.0004665685,0.002010505,0.1457659,0.0009956964,0.0009834896,0.003534332,0.001487303,0.3847943,0.3177778,0.01011527,0.1313452,0.0007237617],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6756948,0.004653341,0.1329766,0.000969703,0.0008540082,0.0009537873,0.01211106,0.1516088,0.02017797],"genre_scores_gemma":[0.8201308,0.0009225133,0.151251,0.000549781,0.0001562834,0.0007732891,0.01421999,0.007646297,0.004350069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007351594,"threshold_uncertainty_score":0.01931304,"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."}}