{"id":"W3198774825","doi":"10.1109/ccece53047.2021.9569061","title":"Code Authorship Attribution using content-based and non-content-based features","year":2021,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Identification (biology); Field (mathematics); Identity (music); Source code; Natural language processing; Artificial intelligence; Natural language; Code (set theory); Writing style; Focus (optics); Computational linguistics; Machine learning; Linguistics; Programming language","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":[0.000854223,0.0002399192,0.0002884303,0.0001220882,0.0003758482,0.0003874291,0.0002889749,0.0002155862,0.00006131161],"category_scores_gemma":[0.0002497898,0.0002208685,0.0001265828,0.0005667416,0.00008375677,0.0003657134,0.0001467202,0.0003204372,0.00002265348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001083034,"about_ca_system_score_gemma":0.0003737253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001057511,"about_ca_topic_score_gemma":0.00009191373,"domain_scores_codex":[0.9978834,0.0002969739,0.0003393796,0.000627008,0.000362081,0.0004911053],"domain_scores_gemma":[0.9984284,0.0002115819,0.0001347873,0.0005133928,0.0004311684,0.0002806911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002071848,0.0004387038,0.07424039,0.0002768691,0.0001231167,0.0005023458,0.0005844726,0.001231548,0.6170322,0.2859682,0.0008020515,0.01859295],"study_design_scores_gemma":[0.001678493,0.00007432273,0.0266462,0.0001173629,0.00003092828,0.00005609481,0.0001845902,0.2497377,0.7195755,0.0004205011,0.0009968237,0.0004815375],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.176988,0.0003330896,0.8171511,0.004529596,0.0004473311,0.0001693736,0.00002192685,0.0002223351,0.0001372045],"genre_scores_gemma":[0.8898009,0.00000279873,0.1067506,0.002526365,0.00005978008,0.000008768917,0.00006187299,0.00001263823,0.0007762692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7128128,"threshold_uncertainty_score":0.9006755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1634173873262401,"score_gpt":0.3116797845410002,"score_spread":0.1482623972147601,"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."}}