{"id":"W2767748721","doi":"10.48550/arxiv.1711.02149","title":"Detecting Disguised Plagiarism","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Plagiarism detection; Computer science; Source code; Preprocessor; Set (abstract data type); Code (set theory); Programming language; Information retrieval; Software engineering; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"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":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["research_integrity"],"domain":null,"study_design":"simulation_or_modeling","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":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.001729044,0.0003018206,0.0003831221,0.0001701477,0.002073889,0.0002367035,0.00204716,0.003243795,0.0003342564],"category_scores_gemma":[0.001337564,0.000367455,0.0002957155,0.0001585212,0.0006709351,0.0003269729,0.0009378816,0.005387564,0.0002808561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004246771,"about_ca_system_score_gemma":0.0006636883,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01461541,"about_ca_topic_score_gemma":0.003099918,"domain_scores_codex":[0.9976588,0.0004821938,0.000201839,0.000852361,0.0001933333,0.0006114568],"domain_scores_gemma":[0.9978129,0.000363347,0.0004918841,0.000827606,0.0002187117,0.0002855253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002179935,0.0001621811,0.02657143,0.0002125447,0.0004769772,0.001256727,0.03007649,0.0128192,0.00005850912,0.9072318,0.01206448,0.008851642],"study_design_scores_gemma":[0.00137923,0.00006056698,0.003088255,0.000809913,0.0006082093,0.000005166392,0.01517787,0.0312668,0.0002642622,0.7250943,0.2196178,0.002627586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5542796,0.000198575,0.02863063,0.00140608,0.003950546,0.0006981808,0.0000765829,0.0005657746,0.410194],"genre_scores_gemma":[0.979516,0.0006624445,0.0001464081,0.0001165924,0.0008151984,8.306713e-7,0.0000167057,0.00002240919,0.0187034],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4252364,"threshold_uncertainty_score":0.9998778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1066676674268585,"score_gpt":0.2394823423565825,"score_spread":0.132814674929724,"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."}}