{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003319979,0.0003261345,0.0003662452,0.000997854,0.001667516,0.001153566,0.002012492,0.0002716052,0.000004722835],"category_scores_gemma":[0.0001489226,0.0003597945,0.00004475309,0.0006792485,0.0005538159,0.00789563,0.003383712,0.001002808,0.000008677358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002569731,"about_ca_system_score_gemma":0.0005360169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002169161,"about_ca_topic_score_gemma":0.00001233313,"domain_scores_codex":[0.9974712,0.0001639932,0.0009456593,0.0005308207,0.0004841613,0.0004041971],"domain_scores_gemma":[0.9969438,0.0004057197,0.0005410447,0.001487146,0.0004501531,0.0001721509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003732485,0.000009838951,0.00003561195,0.00007806916,0.000009552877,4.847579e-7,0.002436493,0.0202562,0.0001366628,0.8262917,0.00009582665,0.1506458],"study_design_scores_gemma":[0.0002104393,0.00002585046,0.00004136709,0.00039629,0.00001076069,0.00001611735,0.00003031592,0.9728543,0.0001654295,0.01185195,0.01404175,0.0003554035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003493551,0.0007146344,0.9858465,0.0004310867,0.0002991275,0.0003598183,0.000111594,0.0001214791,0.01176638],"genre_scores_gemma":[0.3280817,0.002620517,0.6648543,0.001144061,0.00008385708,0.0000330039,0.001993512,0.00001895266,0.001170122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9525981,"threshold_uncertainty_score":0.9998854,"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."}}