{"id":"W3003877329","doi":"10.1145/1227504.1227324","title":"Plagiarism detection using feature-based neural networks","year":2007,"lang":"en","type":"article","venue":"ACM SIGCSE Bulletin","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Plagiarism detection; Feature (linguistics); Relevance (law); Computer science; Detector; Artificial neural network; Similarity (geometry); Artificial intelligence; Code (set theory); Feature engineering; Measure (data warehouse); Pattern recognition (psychology); Natural language processing; Machine learning; Data mining; Deep learning; Programming language; Linguistics","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":"bench_or_experimental","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","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":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.003364227,0.0001714602,0.0001744391,0.0001054986,0.0009298486,0.00008549496,0.000511174,0.001520884,0.0005739043],"category_scores_gemma":[0.001882436,0.0001731522,0.0001122974,0.0003335614,0.0002427333,0.00007544096,0.00006809972,0.002413736,0.00009312084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001893251,"about_ca_system_score_gemma":0.000072898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005230187,"about_ca_topic_score_gemma":0.001152847,"domain_scores_codex":[0.9980099,0.0003154592,0.0002374402,0.0002967288,0.0004618161,0.0006786991],"domain_scores_gemma":[0.9982427,0.001028002,0.000142482,0.0002706193,0.0001187093,0.0001974839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003119211,0.0007368583,0.03409246,0.0001185065,0.0003023529,0.0009296937,0.02970461,0.04937646,0.01213811,0.01873458,0.253836,0.5969112],"study_design_scores_gemma":[0.0006703114,0.00007302253,0.00160424,0.00004755921,0.00005682033,0.00001519145,0.001926803,0.02207999,0.003689965,0.001040263,0.9682235,0.000572364],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6236551,0.0008662242,0.3117082,0.02956501,0.004523175,0.0008673683,0.000007944262,0.0006760844,0.02813092],"genre_scores_gemma":[0.9906035,0.00001877358,0.00325556,0.003188491,0.001629478,0.000003415601,0.000006485292,0.00002023632,0.001274075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7143875,"threshold_uncertainty_score":0.9998878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02276400814018628,"score_gpt":0.2937078578585832,"score_spread":0.270943849718397,"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."}}