{"id":"W4403401272","doi":"10.1007/978-3-031-64954-7_24","title":"Learning AI Coding Style for Software Plagiarism Detection","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Style (visual arts); Coding (social sciences); Computer science; Plagiarism detection; Software; Artificial intelligence; Programming language; Art; Sociology; Visual arts; Social science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["research_integrity"],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009136116,0.0007555471,0.0003848211,0.001788272,0.0003489181,0.001152877,0.001190023,0.0007431,0.003839894],"category_scores_gemma":[0.00806716,0.0002239788,0.000568263,0.0009150055,0.000352313,0.002045354,0.0008464238,0.001692865,0.00240262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006751952,"about_ca_system_score_gemma":0.000684082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00205134,"about_ca_topic_score_gemma":0.003456374,"domain_scores_codex":[0.9993592,0.0001698712,0.00004007442,0.0001828455,0.0001935478,0.0000545387],"domain_scores_gemma":[0.9955269,0.002345806,0.0002647224,0.0005655425,0.001113734,0.0001832549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002421987,0.0002171917,0.007918745,0.0001016518,0.00003300533,0.00004748373,0.0001794302,0.01735126,0.01009772,0.004238943,0.009928041,0.9496443],"study_design_scores_gemma":[0.0000289101,0.0001469414,0.002316511,0.0000363717,0.00002850234,0.0001056717,0.0001430365,0.9621983,0.008913321,0.02227571,0.003786839,0.00001995293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1689981,0.0008009242,0.8004719,0.000617423,0.0002633235,0.0001867778,0.0009204384,0.011013,0.01672805],"genre_scores_gemma":[0.6517821,0.000398354,0.3315408,0.0002807018,0.0001200699,0.0001583987,0.00221716,0.0005002343,0.01300215],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003839894,"threshold_uncertainty_score":0.0128457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01488522899603356,"score_gpt":0.2480336423682532,"score_spread":0.2331484133722196,"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."}}