{"id":"W4214842455","doi":"10.21742/ajemr.2020.5.3.01","title":"Developing Machine Learning Coding Similarity Indicators for C and C++ Corpuses","year":2020,"lang":"en","type":"article","venue":"Asia-Pacific Journal of Educational Management Research","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Plagiarism detection; Computer science; Copying; Programmer; Coding (social sciences); Source code; Similarity (geometry); Personalization; Lexical analysis; Information retrieval; Artificial intelligence; World Wide Web; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007399333,0.001265806,0.0009380119,0.01654448,0.001709649,0.00383216,0.002124867,0.001774503,0.003687962],"category_scores_gemma":[0.05688606,0.0004978169,0.001011489,0.008107741,0.001256747,0.004792815,0.003055546,0.002093004,0.002675345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002094698,"about_ca_system_score_gemma":0.002264736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006301005,"about_ca_topic_score_gemma":0.007782395,"domain_scores_codex":[0.9922258,0.001896122,0.00112159,0.001871855,0.002411318,0.0004733716],"domain_scores_gemma":[0.9702143,0.01433715,0.003223117,0.002751184,0.008752217,0.0007219772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005197637,0.0004812469,0.03862145,0.00114292,0.000156755,0.0004818664,0.002108813,0.02017337,0.01932269,0.01334705,0.02149849,0.8821456],"study_design_scores_gemma":[0.0001271254,0.0007586283,0.08765803,0.0005174816,0.0001286177,0.001182337,0.005390861,0.7745451,0.05855657,0.02414998,0.04670079,0.0002844422],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3282678,0.001965732,0.6162185,0.000781326,0.0008073897,0.002475039,0.009881338,0.02024164,0.01936126],"genre_scores_gemma":[0.3808878,0.0004199457,0.593707,0.0001102727,0.0001183002,0.001770635,0.01873766,0.0007026216,0.003545708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01654448,"threshold_uncertainty_score":0.03913188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08920997880325443,"score_gpt":0.3882725270530651,"score_spread":0.2990625482498107,"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."}}