{"id":"W1895441878","doi":"10.4230/dagsemproc.06301.7","title":"Detection of Plagiarism in University Projects Using Metrics-based Spectral Similarity","year":2007,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Software Engineering Research","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Plagiarism detection; Similarity (geometry); Computer science; Spectral analysis; Source code; Data mining; Clan; Information retrieval; Artificial intelligence; Programming language; Physics","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002543228,0.0005795935,0.001066194,0.01427349,0.000858112,0.001746208,0.0009041701,0.0008156213,0.001018724],"category_scores_gemma":[0.0206524,0.0002673377,0.0005403699,0.008216036,0.0007084139,0.00241819,0.001611441,0.0006302497,0.000737093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007712278,"about_ca_system_score_gemma":0.000704962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001222029,"about_ca_topic_score_gemma":0.001326515,"domain_scores_codex":[0.9939207,0.0009898143,0.0005598473,0.0008513083,0.00340765,0.0002707743],"domain_scores_gemma":[0.9833477,0.004986032,0.003432642,0.001927872,0.005551481,0.0007542248],"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":[0.0009378669,0.0004036856,0.09253872,0.0005399409,0.0002845683,0.0004547162,0.001634252,0.01378039,0.09432578,0.006148288,0.003286421,0.7856653],"study_design_scores_gemma":[0.0001111305,0.001097794,0.2039321,0.0001117768,0.0001598586,0.004932876,0.001465527,0.6420588,0.1159069,0.01903327,0.01087236,0.0003175608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5270267,0.0008200661,0.463793,0.0002045934,0.00006234107,0.0002949605,0.0007783643,0.004055218,0.002964765],"genre_scores_gemma":[0.8299459,0.000194052,0.1675661,0.00002430027,0.00004033661,0.000178155,0.001110716,0.0001664407,0.000773883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9991844,"threshold_uncertainty_score":0.01345003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02642885969981242,"score_gpt":0.2678502540887758,"score_spread":0.2414213943889633,"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."}}