{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001461963,0.0001044633,0.0001584925,0.0006972156,0.0003834163,0.0002024652,0.0006470869,0.00003675197,0.00002577579],"category_scores_gemma":[0.0007176589,0.0001002652,0.00005038524,0.0009522555,0.00008738216,0.0005649544,0.0003379512,0.0004753776,0.000004848839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001555695,"about_ca_system_score_gemma":0.0001966414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002371128,"about_ca_topic_score_gemma":7.489645e-7,"domain_scores_codex":[0.9983567,0.0001452451,0.0003574545,0.0002690766,0.0005932298,0.0002782861],"domain_scores_gemma":[0.9983426,0.0006900874,0.0002375244,0.000133484,0.0004255927,0.0001706611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009209797,0.0001071577,0.01204487,0.0003392984,0.0001468038,0.0000151225,0.001259082,0.00007527367,0.0005904476,0.8947496,0.007403517,0.08317678],"study_design_scores_gemma":[0.002011304,0.002048312,0.02812528,0.000517615,0.00005243985,0.0002536538,0.006740445,0.009802959,0.01907088,0.3044475,0.6259849,0.0009446894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003714846,0.0004120345,0.9425648,0.0498943,0.0001774178,0.0004151989,0.000002045513,0.00003865884,0.002780736],"genre_scores_gemma":[0.7164197,0.0005214245,0.2823944,0.0001436029,0.0001489958,0.00003170284,0.000002817521,0.00001183613,0.0003255418],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7127048,"threshold_uncertainty_score":0.4088697,"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."}}