{"id":"W2042368861","doi":"10.1109/vast.2012.6400484","title":"Relative N-gram signatures: Document visualization at the level of character N-grams","year":2012,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Boeing","keywords":"Visualization; n-gram; Computer science; Classifier (UML); Character (mathematics); Artificial intelligence; Gram; Data visualization; Natural language processing; Pattern recognition (psychology); Information retrieval; Mathematics; Language model","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":[0.0007839651,0.00009171454,0.00009484315,0.00003741444,0.0001490488,0.00003685847,0.0003199817,0.00007708369,0.0002059389],"category_scores_gemma":[0.00006229294,0.00005478708,0.0000584341,0.0002897487,0.00004404999,0.0006709194,0.0002143117,0.0001109966,0.0001384462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005403149,"about_ca_system_score_gemma":0.00001950914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000167798,"about_ca_topic_score_gemma":0.000005920038,"domain_scores_codex":[0.998993,0.0001635407,0.0002060968,0.000143096,0.0002681786,0.0002261204],"domain_scores_gemma":[0.9992584,0.0001594127,0.000135376,0.0002923433,0.00008675083,0.00006769566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005834834,0.0000379335,0.002384942,0.000005984162,0.00001773641,1.795279e-7,0.003019311,0.00001232819,0.001579716,0.9869825,0.0009352801,0.005018246],"study_design_scores_gemma":[0.001450797,0.0003449866,0.1431516,0.0001215709,0.00007367831,0.00002643631,0.0006418147,0.02852874,0.5830364,0.03410595,0.2073529,0.001165155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01605085,0.0002277029,0.9789082,0.001309888,0.0004764066,0.0002091309,0.000004097276,0.00007485859,0.002738819],"genre_scores_gemma":[0.9887531,0.00001039962,0.004486207,0.000655498,0.00006248894,0.00001021178,0.00001571719,0.000004719334,0.006001601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.974422,"threshold_uncertainty_score":0.2254886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09470629678166564,"score_gpt":0.341107670361583,"score_spread":0.2464013735799173,"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."}}