{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001147844,0.0001735398,0.0003619554,0.0001866372,0.0001292361,0.0001194297,0.0005767898,0.0001335666,0.000009004241],"category_scores_gemma":[0.00006632313,0.0001644313,0.0002542583,0.000271019,0.00002393933,0.001227324,0.0002128152,0.0004249057,0.00001050573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002194327,"about_ca_system_score_gemma":0.00007028939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005668368,"about_ca_topic_score_gemma":0.000001343638,"domain_scores_codex":[0.9984249,0.0001437661,0.0005103694,0.0003200594,0.0003635336,0.0002373365],"domain_scores_gemma":[0.9974806,0.0007894546,0.0006094967,0.0003176442,0.0006842088,0.0001185523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002294804,0.001706154,0.07615655,0.0007574608,0.001159165,0.0001632812,0.005422983,0.0213473,0.03195869,0.2126212,0.01266834,0.6337441],"study_design_scores_gemma":[0.002616169,0.002593245,0.1362851,0.0004267247,0.0000494288,0.0002183582,0.00001435813,0.4402391,0.06344856,0.3369326,0.01651047,0.00066591],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3188087,0.000108011,0.6784512,0.00022197,0.00197628,0.0003028441,0.000008074785,0.0001141392,0.000008711694],"genre_scores_gemma":[0.8159293,0.000007164837,0.1832832,0.0001589831,0.0005954537,0.00000991009,0.000003154889,0.000009115231,0.000003778332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6330782,"threshold_uncertainty_score":0.6705313,"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."}}