{"id":"W1969795835","doi":"10.1145/1227310.1227324","title":"Plagiarism detection using feature-based neural networks","year":2007,"lang":"en","type":"article","venue":"","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Plagiarism detection; Computer science; Feature (linguistics); Relevance (law); Detector; Artificial neural network; Similarity (geometry); Artificial intelligence; Feature engineering; Code (set theory); Similarity measure; Feature extraction; Measure (data warehouse); Pattern recognition (psychology); Machine learning; Data mining; Deep learning; Programming language","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":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002452533,0.00009363863,0.00009666618,0.00007852547,0.000715593,0.00005964297,0.0001640747,0.00126747,0.0001945828],"category_scores_gemma":[0.0002064851,0.00008664904,0.00006747726,0.0003289897,0.0001515271,0.0001821843,0.00001408086,0.001710086,0.00001238635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001432949,"about_ca_system_score_gemma":0.0000620642,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00745536,"about_ca_topic_score_gemma":0.007079286,"domain_scores_codex":[0.9987832,0.0001461457,0.000138822,0.0001657557,0.0003158797,0.0004501967],"domain_scores_gemma":[0.9993285,0.0003102544,0.00006299621,0.00008368657,0.00008025499,0.0001343184],"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":[0.001100178,0.000340942,0.05598838,0.00004624467,0.0001567172,0.0002338711,0.02209204,0.07192818,0.01051118,0.1639439,0.02233171,0.6513266],"study_design_scores_gemma":[0.0005912604,0.00006350077,0.003806548,0.00002617864,0.00004995465,0.00001184466,0.004466736,0.8310791,0.006111513,0.002086733,0.1510987,0.0006079465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1276132,0.0001034087,0.8149264,0.001150742,0.001423162,0.0001690488,7.59314e-7,0.0002041872,0.05440903],"genre_scores_gemma":[0.9938959,0.000005602993,0.001944957,0.001675096,0.001080118,7.769521e-7,0.000002293808,0.000007820102,0.001387472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8662826,"threshold_uncertainty_score":0.9991541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02383288585388381,"score_gpt":0.3070886043220694,"score_spread":0.2832557184681856,"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."}}