{"id":"W140340549","doi":"10.63317/2id75yrzanby","title":"Using the Complexity of the Distribution of Lexical Elements as a Feature in Authorship Attribution","year":2008,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Punctuation; Authorship attribution; Computer science; Artificial intelligence; Natural language processing; Feature (linguistics); Support vector machine; Noun; Linguistics","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":[0.001046712,0.000103624,0.0001696409,0.000033681,0.0002512768,0.00001462828,0.0006927329,0.000113256,0.00001644365],"category_scores_gemma":[0.0001801315,0.00005995562,0.0001067805,0.000929201,0.0003986393,0.000165327,0.0002739172,0.0003068031,0.000003089856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009730806,"about_ca_system_score_gemma":0.0001411463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002172437,"about_ca_topic_score_gemma":0.00003635118,"domain_scores_codex":[0.9983695,0.000428267,0.0003603963,0.0001952371,0.0004102092,0.0002364003],"domain_scores_gemma":[0.9990925,0.00007466409,0.0002198459,0.0004310639,0.0001375039,0.00004441907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002598195,0.00009773007,0.1018176,0.00001583825,0.00001025988,0.00000181042,0.0006843865,0.0002005489,0.002196193,0.8943657,0.0002302221,0.0003537316],"study_design_scores_gemma":[0.0007325177,0.00008785873,0.7071111,0.00009556694,0.00001482624,0.00008253819,0.0001290336,0.1496682,0.09043979,0.05020055,0.001209957,0.0002280796],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5895334,0.00003683734,0.4068337,0.003075758,0.0001460903,0.0002032126,0.00001963789,0.00002154734,0.0001298223],"genre_scores_gemma":[0.9960437,0.000003455339,0.003720817,0.0001076719,0.00001908308,0.000002899315,0.0000175006,0.000002587624,0.0000823228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8441651,"threshold_uncertainty_score":0.2444919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2062589589989079,"score_gpt":0.3485729465110212,"score_spread":0.1423139875121133,"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."}}