{"id":"W4285194931","doi":"10.1109/tse.2022.3177228","title":"SCS-Gan: Learning Functionality-Agnostic Stylometric Representations for Source Code Authorship Verification","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Source code; Code (set theory); Set (abstract data type); Task (project management); Benchmark (surveying); Malware; Artificial intelligence; Adversarial system; Representation (politics); Information retrieval; Machine learning; Natural language processing; Programming language; Computer security","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008756905,0.0001948605,0.0001754498,0.0006429685,0.001257758,0.0001224822,0.0004449919,0.00007848498,0.0001164117],"category_scores_gemma":[0.0004280901,0.0002476356,0.0001717435,0.001906276,0.00001729804,0.0003473812,0.000008019891,0.0007432516,0.00003101691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002761015,"about_ca_system_score_gemma":0.00008560176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001188078,"about_ca_topic_score_gemma":0.000001263142,"domain_scores_codex":[0.9981343,0.0001556292,0.000349289,0.000528257,0.0004675481,0.0003650305],"domain_scores_gemma":[0.9978354,0.001361821,0.000108628,0.0004236985,0.0001244216,0.000146019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001786257,0.00006934605,0.0001266525,0.00002935024,0.00003290869,0.000001399212,0.0005377482,0.9884565,0.0005117213,0.00165592,0.00007910574,0.008481458],"study_design_scores_gemma":[0.0007057957,0.0002731718,0.001324818,0.00002571368,0.00005503667,0.00004236059,0.0001898732,0.9566229,0.01000126,0.0002701354,0.02994303,0.0005459306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005048027,0.00007685806,0.9911576,0.0003259918,0.001682088,0.0003888439,0.00006579357,0.001240571,0.00001425436],"genre_scores_gemma":[0.9386199,0.000005724708,0.0591912,0.0000927512,0.00007030037,0.0006671936,0.00004333971,0.00003822661,0.001271369],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9335719,"threshold_uncertainty_score":0.9999976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03621979625623392,"score_gpt":0.2699609822255617,"score_spread":0.2337411859693278,"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."}}