{"id":"W4413323615","doi":"10.1016/j.bdr.2025.100555","title":"Explainable malware detection through integrated graph reduction and learning techniques","year":2025,"lang":"en","type":"article","venue":"Big Data Research","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Malware; Reduction (mathematics); Big data; Graph; Artificial intelligence; Data science; Machine learning; Deep learning; Computer security; Theoretical computer science; Data mining; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002076346,0.0001449616,0.0001511544,0.0007764096,0.0008557141,0.0003535619,0.00131558,0.0001480313,0.000005805183],"category_scores_gemma":[0.0008303836,0.0001413322,0.00002062089,0.002765945,0.0002015903,0.001881188,0.00211766,0.001034405,0.000009574987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001587305,"about_ca_system_score_gemma":0.0001250272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008746278,"about_ca_topic_score_gemma":0.00007942537,"domain_scores_codex":[0.9975306,0.000543387,0.0002298388,0.0008692734,0.0003999871,0.0004269102],"domain_scores_gemma":[0.9978488,0.0001841163,0.00005722564,0.001398804,0.0004553805,0.00005565282],"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":[0.00003603465,0.00003423274,0.00003537919,0.00005917577,0.00001284151,0.000008411734,0.000138679,0.000001966738,0.04224074,0.003983034,0.002299038,0.9511505],"study_design_scores_gemma":[0.0001502331,0.0002581335,0.00008048946,0.0001369601,0.000003776366,0.00005853246,0.0006370849,0.003012876,0.6853848,0.02318755,0.2868917,0.0001978786],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001504182,0.0005263659,0.9936334,0.0005339556,0.0002251905,0.0004695443,0.000009642308,0.001143456,0.001954274],"genre_scores_gemma":[0.6792323,0.002559094,0.3124769,0.0000739488,0.000164311,0.0004375924,0.0001116378,0.00003522693,0.004908975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9509526,"threshold_uncertainty_score":0.6581548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1808340169138115,"score_gpt":0.4031757345333891,"score_spread":0.2223417176195776,"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."}}