{"id":"W4386471798","doi":"10.1186/s42400-023-00183-8","title":"Use of subword tokenization for domain generation algorithm classification","year":2023,"lang":"en","type":"article","venue":"Cybersecurity","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lexical analysis; Computer science; Artificial intelligence; Word (group theory); Convolutional neural network; Feature (linguistics); Domain (mathematical analysis); Scheme (mathematics); Machine learning; Natural language processing; Mathematics","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":[0.001462939,0.000741331,0.0008217745,0.003038979,0.0006177109,0.001529022,0.001281148,0.0006756603,0.00238662],"category_scores_gemma":[0.005815296,0.0001644121,0.0005986827,0.002056671,0.0004426383,0.002270909,0.001207267,0.001022143,0.00192539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008600656,"about_ca_system_score_gemma":0.001423013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003337485,"about_ca_topic_score_gemma":0.003324644,"domain_scores_codex":[0.9983186,0.0004868476,0.0002068783,0.0004629189,0.0003361375,0.0001888198],"domain_scores_gemma":[0.9962728,0.001215169,0.0004359384,0.0008558608,0.000970404,0.000249785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009717415,0.0003282984,0.02520943,0.0001908928,0.0001137768,0.000208517,0.0001961333,0.02553976,0.02635922,0.004999776,0.007981365,0.907901],"study_design_scores_gemma":[0.00003252528,0.0001428416,0.004218621,0.0000163078,0.00005433119,0.000164532,0.0001074711,0.956163,0.03158117,0.003273756,0.004210801,0.00003466633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3487353,0.001008453,0.6323782,0.0003784527,0.0004583313,0.0004396438,0.001268638,0.01085228,0.004480673],"genre_scores_gemma":[0.8196653,0.0001738458,0.1742599,0.00009116919,0.00007812049,0.0001541212,0.002850176,0.0002264843,0.002500964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003337485,"threshold_uncertainty_score":0.007984042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1179084249451668,"score_gpt":0.2921493607814226,"score_spread":0.1742409358362558,"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."}}