{"id":"W2250418537","doi":"","title":"Author Verification Using Common N-Gram Profiles of Text Documents","year":2014,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; n-gram; Natural language processing; Artificial intelligence; Classifier (UML); Set (abstract data type); Class (philosophy); Identification (biology); Information retrieval; 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":[0.0006286454,0.00007428353,0.0001167324,0.00006465892,0.00009283494,0.00005754299,0.0003914578,0.00005597857,0.00003800663],"category_scores_gemma":[0.00005475475,0.00006469634,0.00003647517,0.0002627148,0.00003001938,0.0002955906,0.00009827406,0.00007001748,0.000048028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002291673,"about_ca_system_score_gemma":0.00002694605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005512061,"about_ca_topic_score_gemma":0.000002053345,"domain_scores_codex":[0.9991032,0.0001330671,0.0002325032,0.0001932689,0.0001904423,0.0001475443],"domain_scores_gemma":[0.9993031,0.00005583279,0.0001289439,0.0003816454,0.00007353876,0.0000569406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007900388,0.00007494116,0.01094826,0.00004102874,0.00001188836,3.479472e-7,0.0005088106,0.0001914763,0.02668149,0.8865303,0.0005051162,0.07449844],"study_design_scores_gemma":[0.0003195123,0.00009755305,0.01101636,0.00004337673,0.000009608407,0.00000546335,0.00005447866,0.7385574,0.2253108,0.0142758,0.01005809,0.0002515303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1116635,0.00001506267,0.8843619,0.0005573091,0.0002275171,0.0001222878,9.268531e-7,0.0001111195,0.002940353],"genre_scores_gemma":[0.9115201,6.482445e-7,0.08782717,0.00009041251,0.00002517142,0.000003539105,0.000004590915,0.000003672514,0.0005246841],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8722545,"threshold_uncertainty_score":0.263824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04998160390730941,"score_gpt":0.3299500645796463,"score_spread":0.2799684606723369,"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."}}