{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00144248,0.001692465,0.001374495,0.002163565,0.0006468235,0.001934788,0.002613355,0.001360586,0.003079867],"category_scores_gemma":[0.006230668,0.0006448138,0.001120341,0.001144116,0.0006557492,0.002533412,0.001251074,0.002351393,0.003929606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009652904,"about_ca_system_score_gemma":0.001990289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007443449,"about_ca_topic_score_gemma":0.01423579,"domain_scores_codex":[0.9986958,0.0002755208,0.0001199341,0.0004006784,0.000364122,0.0001440796],"domain_scores_gemma":[0.9974853,0.001029204,0.0002894392,0.0004399216,0.0006349887,0.0001212136],"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":[0.0003531972,0.0003771617,0.003253749,0.0002016677,0.000129039,0.0002457147,0.0001617123,0.09618541,0.01402297,0.006400487,0.0140256,0.8646433],"study_design_scores_gemma":[0.00001671451,0.0000713959,0.0002382729,0.00001704095,0.00001670331,0.0000802314,0.00002474524,0.9858755,0.006867266,0.005046681,0.001723713,0.0000217138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02708401,0.0007283979,0.9451281,0.0003253325,0.0001339805,0.0001772542,0.0008469588,0.02383507,0.001740988],"genre_scores_gemma":[0.2917205,0.0005652414,0.694317,0.0006048742,0.0001421158,0.0004242742,0.00450396,0.0009940434,0.006728032],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007443449,"threshold_uncertainty_score":0.01480025,"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."}}