{"id":"W2515051907","doi":"10.1145/2960811.2960817","title":"Using a Dictionary and n-gram Alignment to Improve Fine-grained Cross-Language Plagiarism Detection","year":2016,"lang":"en","type":"article","venue":"","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; University of Tehran","keywords":"Computer science; Plagiarism detection; Similarity (geometry); Focus (optics); Cross-language information retrieval; Information retrieval; Natural language processing; Precision and recall; Artificial intelligence; Machine translation; n-gram; Range (aeronautics); Language model","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001328061,0.001172439,0.001208967,0.006233114,0.001207248,0.00135066,0.0009362074,0.001087386,0.002913422],"category_scores_gemma":[0.009868345,0.0003422558,0.000661289,0.005487588,0.0005901862,0.002703657,0.001981891,0.001270372,0.003529588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005889317,"about_ca_system_score_gemma":0.001611415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004109603,"about_ca_topic_score_gemma":0.008540954,"domain_scores_codex":[0.9977953,0.0005586727,0.0003019417,0.0005182843,0.0006714669,0.0001544138],"domain_scores_gemma":[0.9955232,0.001114203,0.0007615972,0.0008941602,0.001495737,0.0002111449],"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":[0.0006114203,0.0004220848,0.0159346,0.000824171,0.0001988021,0.0004509171,0.000966169,0.006848872,0.0916094,0.003683542,0.01047858,0.8679715],"study_design_scores_gemma":[0.000193294,0.0009806576,0.04359396,0.0001752784,0.0003943269,0.002814838,0.001817019,0.7598152,0.1348568,0.01826483,0.03681854,0.0002752915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1766815,0.001715233,0.8002912,0.0004446382,0.0002368074,0.0005490591,0.00189018,0.01151044,0.006680777],"genre_scores_gemma":[0.4477253,0.0005915496,0.5428544,0.0001593956,0.0001287619,0.0002430671,0.003848426,0.0004942396,0.003954854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9989126,"threshold_uncertainty_score":0.009746373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01922021491713604,"score_gpt":0.3318187537036996,"score_spread":0.3125985387865635,"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."}}