{"id":"W4409507688","doi":"10.1007/978-3-031-85856-7_13","title":"AuthAttLyzer-V2: Unveiling Code Authorship Attribution Using Enhanced Ensemble Learning Models and Generating Benchmark Dataset","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Benchmark (surveying); Computer science; Attribution; Code (set theory); Artificial intelligence; Authorship attribution; Natural language processing; Ensemble learning; Information retrieval; Machine learning; Programming language; Psychology; Cartography; Geography","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":[0.002939797,0.002559097,0.0009941331,0.003850046,0.001249537,0.001868728,0.002555117,0.001974995,0.005214461],"category_scores_gemma":[0.008833375,0.0005176574,0.001537616,0.002684282,0.0005518908,0.001989037,0.002415117,0.00234207,0.006898655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003523,"about_ca_system_score_gemma":0.001565925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01090912,"about_ca_topic_score_gemma":0.02622076,"domain_scores_codex":[0.9976922,0.0006301562,0.0001202838,0.0006613573,0.0006405477,0.0002554167],"domain_scores_gemma":[0.9954389,0.001268683,0.0001545284,0.001771611,0.001099897,0.0002664905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007257421,0.00120669,0.01695158,0.0005651005,0.0003807317,0.0002941855,0.0002345136,0.0514827,0.008919076,0.003050757,0.5566112,0.3595778],"study_design_scores_gemma":[0.0003229972,0.0005883594,0.01273319,0.0001706101,0.0001835923,0.0005677635,0.0004406377,0.8400486,0.03768273,0.01477082,0.09233581,0.0001548455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3952427,0.003678113,0.2466591,0.002171804,0.004063913,0.001359667,0.1853066,0.1352818,0.0262364],"genre_scores_gemma":[0.255773,0.0005846854,0.2709211,0.0006621411,0.0002947273,0.0008921221,0.4432575,0.004726273,0.02288856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01090912,"threshold_uncertainty_score":0.0216912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1279730438806615,"score_gpt":0.3464217794647094,"score_spread":0.2184487355840478,"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."}}