{"id":"W2975826887","doi":"10.3233/jcs-191292","title":"Decoupling coding habits from functionality for effective binary authorship attribution","year":2019,"lang":"en","type":"article","venue":"Journal of Computer Security","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Binary number; Code refactoring; Source code; Coding (social sciences); Binary code; Compiler; Reverse engineering; Programming language; Software","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":[0.004053225,0.001004755,0.001116631,0.004770921,0.00102522,0.003350473,0.001285012,0.001204657,0.002944232],"category_scores_gemma":[0.04175685,0.0006721732,0.0006597344,0.003095004,0.001110355,0.007030453,0.004259519,0.001579793,0.004423989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000839424,"about_ca_system_score_gemma":0.001959535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001154063,"about_ca_topic_score_gemma":0.002410385,"domain_scores_codex":[0.9935439,0.001003308,0.0009715401,0.0019028,0.00221556,0.0003629441],"domain_scores_gemma":[0.9686941,0.009227023,0.006016966,0.01058847,0.004745922,0.0007276302],"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":[0.0006529423,0.000360513,0.09225866,0.0009225797,0.0001123572,0.0004591066,0.00239121,0.005956659,0.02742776,0.009376639,0.03648286,0.8235987],"study_design_scores_gemma":[0.0001285872,0.0003306578,0.06946644,0.0005354126,0.000181492,0.002360484,0.001713242,0.5456227,0.1757781,0.08385024,0.1195162,0.0005163701],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2058464,0.001070139,0.6627768,0.001153838,0.0005790466,0.0006036311,0.005247312,0.113331,0.009391808],"genre_scores_gemma":[0.6540418,0.0004339528,0.3201716,0.0005005313,0.0002141079,0.0004307001,0.01090275,0.00569939,0.007605167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004770921,"threshold_uncertainty_score":0.02143574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01485298257875823,"score_gpt":0.2771072211113607,"score_spread":0.2622542385326025,"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."}}