{"id":"W4402807503","doi":"10.1109/tdsc.2024.3449641","title":"NeuroYara: Learning to Rank for Yara Rules Generation Through Deep Language Modeling and Discriminative N-Gram Encoding","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Dependable and Secure Computing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminative model; n-gram; Computer science; Encoding (memory); Gram; Rank (graph theory); Artificial intelligence; Language model; Natural language processing; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002714063,0.0001975424,0.0001804063,0.0001819797,0.0005994291,0.0007434317,0.0002012774,0.00008011737,0.000001646341],"category_scores_gemma":[0.00002108023,0.0001787077,0.00005708006,0.0002617099,0.00001932153,0.0006823933,0.00001554245,0.0003798919,0.000001816322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003705136,"about_ca_system_score_gemma":0.00002538665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006227555,"about_ca_topic_score_gemma":0.00003714997,"domain_scores_codex":[0.9987324,0.0000606198,0.000208281,0.0005665126,0.0001566865,0.0002754391],"domain_scores_gemma":[0.999479,0.0002158088,0.00003516232,0.0001363239,0.00006527422,0.00006846358],"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":[0.00002275468,0.00004103633,0.000001487825,0.0003452738,0.00005191067,0.0000595243,0.04118733,0.1526026,0.02898201,0.01377031,0.00003548554,0.7629004],"study_design_scores_gemma":[0.000127277,0.000117371,2.974488e-7,0.0001870846,0.00002470148,0.00005163143,0.0004038311,0.9653214,0.03164836,0.00181206,0.0000952454,0.0002107667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06033673,0.003022562,0.9350101,0.0003763193,0.0003146435,0.0002881468,0.000004998097,0.0006030959,0.00004345025],"genre_scores_gemma":[0.7350615,0.00004673091,0.2645959,0.0001309988,0.00008340143,0.00001766559,0.000002999482,0.0000183386,0.00004249617],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8127188,"threshold_uncertainty_score":0.7287487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02465433547219473,"score_gpt":0.2976123308965028,"score_spread":0.272957995424308,"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."}}