{"id":"W2123407642","doi":"10.1016/j.diin.2008.05.001","title":"A novel approach of mining write-prints for authorship attribution in e-mail forensics","year":2008,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Authorship attribution; Suspect; Computer science; Attribution; Decision tree; Support vector machine; Quality (philosophy); Information retrieval; Data mining; Data science; Computer security; Artificial intelligence; Psychology","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":[0.0005880459,0.0001257471,0.0001803054,0.0001582565,0.00009686949,0.00007408536,0.0002830893,0.0001295457,7.224609e-7],"category_scores_gemma":[0.0005785129,0.0001338602,0.00007016669,0.0006446182,0.0001327723,0.001096047,0.00008485364,0.0001150394,0.00000662319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000777742,"about_ca_system_score_gemma":0.0001436396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009026015,"about_ca_topic_score_gemma":0.000001829795,"domain_scores_codex":[0.9987491,0.00003488433,0.000414119,0.000314331,0.0002379934,0.0002495415],"domain_scores_gemma":[0.9991412,0.0001406906,0.000196482,0.0002310603,0.0001834964,0.0001070769],"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":[0.00005850515,0.0002287331,0.1257036,0.0002279938,0.00002654836,0.000004039815,0.01060731,0.001692689,0.009140586,0.8330095,0.0005534271,0.01874704],"study_design_scores_gemma":[0.002330024,0.0002683406,0.1286588,0.0002232274,0.00001214232,0.00009550866,0.0003589574,0.6942624,0.0834083,0.08865802,0.0009366552,0.0007875805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3699315,0.00001494146,0.6291485,0.0001587332,0.000096752,0.000205598,0.00002208031,0.00005546317,0.0003665125],"genre_scores_gemma":[0.8657624,9.330669e-7,0.1337858,0.00007093789,0.00003114073,0.00003234204,0.0001841592,0.000007344503,0.0001249667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7443514,"threshold_uncertainty_score":0.545866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1382981898189501,"score_gpt":0.2774152743910965,"score_spread":0.1391170845721464,"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."}}