{"id":"W2885961833","doi":"10.1177/0165551518787696","title":"Cross-lingual text alignment for fine-grained plagiarism detection","year":2018,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Institute for Research in Fundamental Sciences; University of Waterloo; University of Tehran","keywords":"Computer science; Plagiarism detection; Similarity (geometry); Natural language processing; Information retrieval; Filter (signal processing); Granularity; Source text; Artificial intelligence; Weighting; Range (aeronautics); Machine translation; Scheme (mathematics); Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["research_integrity"],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"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":[0.002691154,0.00006924563,0.0000953437,0.000387562,0.0003557516,0.0006118511,0.0009450193,0.00004382472,0.000007797449],"category_scores_gemma":[0.0007663314,0.0000551346,0.00005691456,0.0005461573,0.0001632454,0.007682033,0.0001103613,0.0001114387,0.00002486643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301873,"about_ca_system_score_gemma":0.0003291809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004019672,"about_ca_topic_score_gemma":0.000001907421,"domain_scores_codex":[0.9983447,0.0000105528,0.0006103955,0.00009393563,0.0007267102,0.0002136652],"domain_scores_gemma":[0.9976252,0.00006155614,0.0005900146,0.0002226379,0.001396264,0.000104307],"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":[0.00007151128,0.00003724001,0.0003892146,0.00002838411,0.00001315258,0.000001574795,0.01182643,0.006210241,0.02115373,0.02605637,0.0004176024,0.9337946],"study_design_scores_gemma":[0.001169131,0.0006701434,0.003916492,0.00004233459,0.000004924855,0.0002116262,0.0002063886,0.7861269,0.1748008,0.004239646,0.02841193,0.0001997043],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1585195,0.000004462235,0.8389848,0.000292484,0.001280556,0.00008597533,6.69221e-7,0.000018051,0.0008134997],"genre_scores_gemma":[0.8964426,0.000001383508,0.1029252,0.0003507523,0.0002350997,0.000002075251,1.315368e-7,0.000001367724,0.000041466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335948,"threshold_uncertainty_score":0.5900094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02045516974507706,"score_gpt":0.3085947324421366,"score_spread":0.2881395626970595,"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."}}