{"id":"W4406488692","doi":"10.7717/peerj-cs.2504","title":"MSSA: multi-stage semantic-aware neural network for binary code similarity detection","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Centre Scientifique et Technique du Bâtiment; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Binary code; Binary number; Artificial neural network; Artificial intelligence; Transformer; Semantics (computer science); Code (set theory); Source code; Semantic similarity; Deep learning; Machine learning; Data mining; Pattern recognition (psychology); Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001132336,0.000294075,0.000303108,0.0004310765,0.00117601,0.0005253329,0.002439433,0.0001073396,0.000002139953],"category_scores_gemma":[0.0001208395,0.0002979585,0.0001411495,0.002641501,0.0003651978,0.001658034,0.001391725,0.0003015803,0.000006351869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002161179,"about_ca_system_score_gemma":0.0002075354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003344795,"about_ca_topic_score_gemma":0.00009048783,"domain_scores_codex":[0.996953,0.00007515492,0.0004098834,0.001262338,0.0004880913,0.0008115179],"domain_scores_gemma":[0.9976742,0.000242066,0.0001806257,0.001155404,0.0005881413,0.0001595671],"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":[0.00006789983,0.0003311645,0.001391169,0.0002349058,0.00003549842,0.00004756285,0.0004317354,0.1882769,0.01508276,0.01738477,0.004684785,0.7720308],"study_design_scores_gemma":[0.0003621504,0.0002034709,0.004577965,0.00004044184,0.000006228386,0.00001511223,0.000005119496,0.9579393,0.02670351,0.002386935,0.007453853,0.0003058823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004802558,0.00006532074,0.9884794,0.0009970318,0.003183591,0.000747463,0.00001089195,0.001676321,0.0000374406],"genre_scores_gemma":[0.4328654,0.000005335386,0.5655417,0.001026614,0.0001425674,0.00009309352,0.000001735265,0.00001107969,0.0003124764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7717249,"threshold_uncertainty_score":0.9999472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03622750143753793,"score_gpt":0.3262810718075838,"score_spread":0.2900535703700459,"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."}}