{"id":"W2065236871","doi":"10.1145/1869746.1869766","title":"PlagDetect","year":2010,"lang":"en","type":"article","venue":"ACM Inroads","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Plagiarism detection; Java; Context (archaeology); Programming language; Measure (data warehouse); Software engineering; Artificial intelligence; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000168573,0.00008482568,0.00007798736,0.00006680049,0.0000671039,0.0001216285,0.002157226,0.00008605092,0.00002883475],"category_scores_gemma":[0.0004385161,0.00006655012,0.00003264376,0.0002189935,0.00003389784,0.0003791553,0.0005813265,0.0003354269,0.00007840196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006997828,"about_ca_system_score_gemma":0.0000309154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002454244,"about_ca_topic_score_gemma":0.00001670182,"domain_scores_codex":[0.9993505,0.00001158581,0.00008877509,0.00021516,0.0001584545,0.0001754688],"domain_scores_gemma":[0.9987216,0.00006486581,0.00003727496,0.001080842,0.00004344989,0.00005194075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000002220659,0.00003785623,0.002090196,0.000008944818,0.000008636523,0.00004319638,0.0003723792,1.298476e-7,0.2355452,0.2035533,0.0045791,0.5537589],"study_design_scores_gemma":[0.0001740744,0.00006403114,0.00237281,0.00001084582,0.000003267201,0.00008048638,0.000002981036,0.0008673618,0.5213845,0.453554,0.02114451,0.0003411298],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.446431,0.0009459762,0.526732,0.008352119,0.002595676,0.0003033043,0.000002364522,0.006177802,0.008459826],"genre_scores_gemma":[0.5338876,9.937941e-7,0.4655328,0.000391625,0.00003928515,0.000006013839,3.438628e-7,0.000004106649,0.0001372246],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5534178,"threshold_uncertainty_score":0.4008698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0092614352417447,"score_gpt":0.2693851248016546,"score_spread":0.2601236895599099,"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."}}