{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001184376,0.00107917,0.0004794192,0.004954836,0.0006314787,0.002785339,0.0007233349,0.0009550264,0.008730805],"category_scores_gemma":[0.008001673,0.0002542543,0.0003441672,0.003471433,0.0004458349,0.003387381,0.001719779,0.001070086,0.002302919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004168788,"about_ca_system_score_gemma":0.0005524513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001372254,"about_ca_topic_score_gemma":0.001209905,"domain_scores_codex":[0.9994125,0.0001719331,0.00006031923,0.00008736588,0.000215019,0.00005281028],"domain_scores_gemma":[0.9962798,0.001749528,0.0004629134,0.0004458007,0.0008698548,0.0001921035],"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":[0.00158274,0.0001843237,0.008642868,0.001135732,0.0001073524,0.0008830819,0.005632313,0.008884261,0.1091868,0.05044056,0.0678303,0.7454897],"study_design_scores_gemma":[0.000201089,0.000396651,0.01869401,0.0006563774,0.0001619393,0.002410149,0.004243915,0.4465709,0.1472481,0.1487254,0.2303027,0.0003888477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06897633,0.001175898,0.8586186,0.001632552,0.0003855988,0.0002668676,0.00781028,0.04861436,0.01251949],"genre_scores_gemma":[0.3045543,0.000845985,0.6834388,0.0002389381,0.0001871072,0.0002785199,0.003341315,0.002779946,0.004335147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008730805,"threshold_uncertainty_score":0.02920741,"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."}}