{"id":"W1869933348","doi":"10.24908/pceea.v0i0.3164","title":"Plagiarism Detection in Code-Based Assignments","year":2010,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Plagiarism detection; Computer science; Programming language; Code (set theory); Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["research_integrity"],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["research_integrity"],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008512797,0.0001188286,0.0001184891,0.0005571051,0.00009544449,0.0001670493,0.0007384898,0.0002272177,0.000008733551],"category_scores_gemma":[0.004103129,0.0001245759,0.0000520865,0.0009885732,0.00001101949,0.0003560314,0.00004138586,0.0006585223,0.000009791736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00191122,"about_ca_system_score_gemma":0.000930039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005986655,"about_ca_topic_score_gemma":0.01452292,"domain_scores_codex":[0.9987156,0.000006309222,0.0002333048,0.0002255426,0.0004765153,0.0003427115],"domain_scores_gemma":[0.9989038,0.0001713381,0.0001733009,0.0001784478,0.0003798227,0.000193314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000003999383,0.0002315757,0.8376066,0.0003063481,0.00006880653,5.601429e-7,0.001273817,0.006983497,0.1130144,0.01852157,0.007365995,0.01462281],"study_design_scores_gemma":[0.000283,0.00001682856,0.8808327,0.00007666121,0.000006335471,0.000002370198,0.00001902034,0.06442756,0.04351413,0.0002607349,0.01030924,0.0002514166],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851131,0.00002389196,0.004303594,0.004391601,0.004444924,0.000534447,0.00000855185,0.0002486833,0.0009312225],"genre_scores_gemma":[0.9949316,7.156806e-7,0.004378784,0.0001085905,0.00008280197,0.00006940743,0.000001391913,0.00001922731,0.0004074272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06950031,"threshold_uncertainty_score":0.9050072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005096784077251245,"score_gpt":0.2120938383778413,"score_spread":0.20699705430059,"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."}}