{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001365232,0.001043202,0.0008387935,0.00120372,0.0002726062,0.0006426117,0.00143381,0.001191473,0.002082687],"category_scores_gemma":[0.005501262,0.0004116346,0.000807097,0.0006675985,0.0009346869,0.001155905,0.0009632417,0.001673867,0.000972315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009865382,"about_ca_system_score_gemma":0.0007618335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002655791,"about_ca_topic_score_gemma":0.003516235,"domain_scores_codex":[0.9993262,0.000244231,0.00002856495,0.0001728806,0.0001490198,0.00007903993],"domain_scores_gemma":[0.9977843,0.001320562,0.0001923661,0.000301973,0.0003129096,0.00008790781],"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":[0.000352305,0.0002048664,0.006862964,0.0001902966,0.0001437061,0.0002699919,0.0002062815,0.6360524,0.008430443,0.0126526,0.01235854,0.3222756],"study_design_scores_gemma":[0.000005720016,0.00001576133,0.0002603795,0.00000799721,0.000006281106,0.00002959246,0.000005666822,0.9945485,0.0008261348,0.003818102,0.0004705675,0.000005315811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08863712,0.00135828,0.8964856,0.001015924,0.0002756255,0.0001834177,0.0008063173,0.005156362,0.0060813],"genre_scores_gemma":[0.8904487,0.0004877955,0.09579516,0.0008220358,0.0001732098,0.0002246819,0.002022126,0.0002972785,0.009728984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002655791,"threshold_uncertainty_score":0.007220089,"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."}}