{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003341767,0.0001614536,0.0001402622,0.0001026572,0.0001876683,0.0006696037,0.0004055627,0.0001531518,0.00001189089],"category_scores_gemma":[0.0007522777,0.000168913,0.0000697007,0.0003239246,0.0001402299,0.002037882,0.0001057196,0.0001846063,0.0001303682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002984679,"about_ca_system_score_gemma":0.0001217407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001931326,"about_ca_topic_score_gemma":0.00001778493,"domain_scores_codex":[0.9986975,0.00002920694,0.0003275427,0.0004459692,0.0002385128,0.0002612886],"domain_scores_gemma":[0.9987534,0.0002491746,0.0001839559,0.000396068,0.0001908895,0.0002264662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000285302,0.00005564861,0.1132916,0.0000602072,0.0000579792,0.000006662077,0.005682026,0.00009695774,0.1805705,0.5242626,0.006318494,0.1695687],"study_design_scores_gemma":[0.0008776979,0.00008836336,0.0259203,0.0000635148,0.00001404073,0.000009856008,0.000117442,0.1159823,0.3197247,0.5314464,0.005185666,0.0005697375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7538234,0.00001039264,0.2428554,0.001226217,0.0008300653,0.0002652686,0.00003638771,0.0002606181,0.0006922781],"genre_scores_gemma":[0.9068083,3.703437e-7,0.09158251,0.0006663078,0.0002057282,0.00004538142,0.00043433,0.00001346206,0.0002436071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.168999,"threshold_uncertainty_score":0.6888072,"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."}}