{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005135031,0.0006451685,0.000988896,0.01734578,0.001481795,0.002215637,0.001814307,0.001525994,0.002191366],"category_scores_gemma":[0.06612677,0.0004156717,0.000358497,0.007757412,0.0008472262,0.002818284,0.002322934,0.001028696,0.002412908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001148776,"about_ca_system_score_gemma":0.0009741556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002687693,"about_ca_topic_score_gemma":0.003512151,"domain_scores_codex":[0.9845345,0.002676355,0.001481293,0.002463757,0.00820759,0.0006364663],"domain_scores_gemma":[0.910009,0.03241449,0.02340622,0.009222754,0.0217427,0.00320481],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001573685,0.0007046956,0.281908,0.001133805,0.0001716326,0.001406691,0.005496195,0.004339095,0.05468344,0.002706114,0.01487683,0.6309997],"study_design_scores_gemma":[0.0001443366,0.001298581,0.7015165,0.0004180553,0.0001783593,0.006293016,0.002322199,0.1479887,0.1060774,0.00777714,0.02561057,0.0003751187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8894088,0.001977249,0.08582918,0.0003416173,0.0002091393,0.0007670564,0.002740623,0.007606192,0.0111202],"genre_scores_gemma":[0.9315219,0.0003279504,0.05940636,0.00008815282,0.0001174121,0.0002728626,0.002529814,0.0003867514,0.005348845],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.998474,"threshold_uncertainty_score":0.02715695,"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."}}