{"id":"W2125962012","doi":"10.1016/j.diin.2010.03.003","title":"Mining writeprints from anonymous e-mails for forensic investigation","year":2010,"lang":"en","type":"article","venue":"Digital Investigation","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Exploit; Cluster analysis; Stylometry; Anonymity; Identification (biology); Classifier (UML); Cybercrime; Focus (optics); Writing style; Information retrieval; World Wide Web; Data science; Data mining; Artificial intelligence; Computer security; The Internet","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":[0.002736854,0.0007698136,0.000697794,0.01348977,0.001373236,0.002439719,0.0008922673,0.001409183,0.003144258],"category_scores_gemma":[0.02955322,0.0003559741,0.0004821336,0.008154401,0.0005021053,0.002376371,0.00164747,0.0008320834,0.005449221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000383343,"about_ca_system_score_gemma":0.001221121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000434737,"about_ca_topic_score_gemma":0.0009384266,"domain_scores_codex":[0.994091,0.001228553,0.0009818757,0.0007595256,0.002370002,0.0005690475],"domain_scores_gemma":[0.9504859,0.01921589,0.01176661,0.008107142,0.008720583,0.001704051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001261488,0.0006632371,0.3534002,0.001039289,0.0001781805,0.004060037,0.003596753,0.003100144,0.03670503,0.006260365,0.02593942,0.563796],"study_design_scores_gemma":[0.0001058108,0.001097546,0.4096667,0.001001475,0.0007170813,0.01817424,0.01643811,0.1300568,0.203346,0.03048776,0.1886107,0.0002977234],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9057133,0.001623818,0.06044876,0.001000734,0.0004663545,0.0004299869,0.01647409,0.002294646,0.01154833],"genre_scores_gemma":[0.9261526,0.0008444351,0.0465415,0.0001481763,0.000454444,0.0002153361,0.01505832,0.0002181424,0.01036699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01348977,"threshold_uncertainty_score":0.01447403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04413737110212299,"score_gpt":0.2634196282676218,"score_spread":0.2192822571654988,"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."}}