{"id":"W3206885924","doi":"10.1002/stvr.1799","title":"A mutation framework for evaluating security analysis tools in IoT applications","year":2021,"lang":"en","type":"preprint","venue":"Software Testing Verification and Reliability","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Taint checking; Internet of Things; Sensitivity (control systems); Precision and recall; Context (archaeology); Security analysis; Set (abstract data type); Data mining; Process (computing); Domain (mathematical analysis); Information flow; Information retrieval; Computer security; Software; Engineering; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00182656,0.0002730773,0.000466911,0.0003219348,0.0002556565,0.0004734725,0.0005404156,0.0004327725,0.000004020081],"category_scores_gemma":[0.01553046,0.0003100929,0.0001717055,0.001968158,0.00009235778,0.0003057405,0.0004844356,0.0007149883,8.283541e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002989965,"about_ca_system_score_gemma":0.0002990219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001088865,"about_ca_topic_score_gemma":0.00002346966,"domain_scores_codex":[0.9969627,0.0002661759,0.0007622357,0.001449154,0.0003054375,0.0002543067],"domain_scores_gemma":[0.9940093,0.002561984,0.0006279821,0.001584116,0.001126082,0.00009054028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000279585,0.0004973632,0.02706878,0.00192872,0.0001424933,0.000003400678,0.003560679,0.0654598,0.0003384553,0.008099604,0.00001366494,0.8928591],"study_design_scores_gemma":[0.0002037585,0.00008629293,0.06501123,0.000264722,0.0001931167,0.000005645298,0.000163021,0.4129376,0.001135118,0.5192478,0.0001346839,0.000617062],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04529462,0.0002290147,0.9510121,0.0002289709,0.0001478548,0.001838984,0.00003637441,0.001197693,0.00001436978],"genre_scores_gemma":[0.3583991,0.00001650067,0.6394122,0.00005135117,0.00002930413,0.001964024,0.0001115261,0.00001202642,0.000003971987],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.892242,"threshold_uncertainty_score":0.9999351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06271620279564884,"score_gpt":0.3700882404693309,"score_spread":0.3073720376736821,"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."}}