{"id":"W2081401338","doi":"10.1145/1571941.1572146","title":"Using dynamic markov compression to detect vandalism in the wikipedia","year":2009,"lang":"en","type":"article","venue":"","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Compression (physics); Markov chain; Data compression; Markov process; Hidden Markov model; Markov model; Data mining; Machine learning; Dynamic range compression; Artificial intelligence; Mathematics; Statistics; Telecommunications","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":[0.0004954665,0.00003819127,0.00004232361,0.00005312857,0.0002391086,0.00008912062,0.000151894,0.00003650793,0.0001644763],"category_scores_gemma":[0.00009851657,0.00002721863,0.00001176782,0.0005264515,0.00002159946,0.0001134294,0.000005711608,0.00004976471,0.00001393652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008447647,"about_ca_system_score_gemma":0.0001098614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005845244,"about_ca_topic_score_gemma":0.005013492,"domain_scores_codex":[0.9993137,0.000182867,0.00008860585,0.00008678686,0.0002080199,0.0001200857],"domain_scores_gemma":[0.9997514,0.00005334087,0.00002147355,0.00009359983,0.00004406358,0.0000361147],"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":[0.00008589245,0.0003265982,0.003420718,0.00000619778,0.000005388859,0.000006351941,0.2832622,0.001015164,0.01225503,0.09509642,0.04822515,0.5562949],"study_design_scores_gemma":[0.0009423023,0.0001992119,0.2728839,0.0001053922,0.00002386025,0.000003073445,0.1826132,0.00848921,0.0006130122,0.05170098,0.481654,0.0007718199],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8416169,0.00004647649,0.003494747,0.02231854,0.0005675526,0.0003906517,8.536164e-7,0.00004615634,0.1315181],"genre_scores_gemma":[0.9927966,0.00001141377,0.003372372,0.00297535,0.000115645,0.000003906445,0.000001001056,0.000001616983,0.0007220673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5555231,"threshold_uncertainty_score":0.2797646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03020876314626032,"score_gpt":0.3991826432805757,"score_spread":0.3689738801343154,"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."}}