{"id":"W4413845085","doi":"10.1016/j.jss.2025.112603","title":"FIN: Boosting binary code embedding by normalizing function inlinings","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Defence Research and Development Canada","keywords":"Boosting (machine learning); Embedding; Binary number; Fin; Code (set theory); Computer science; Mathematics; Algorithm; Artificial intelligence; Materials science; Arithmetic; Programming language","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":[0.0008623658,0.00141767,0.001033865,0.001541706,0.000517023,0.0008438251,0.001278533,0.001080386,0.006815132],"category_scores_gemma":[0.003504879,0.0004956855,0.0006397875,0.0007787094,0.000674222,0.001957692,0.001579463,0.001351772,0.00368891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004158601,"about_ca_system_score_gemma":0.0006606253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001301456,"about_ca_topic_score_gemma":0.002574854,"domain_scores_codex":[0.9992898,0.0001435816,0.00003080129,0.0001709515,0.0002710076,0.00009387456],"domain_scores_gemma":[0.9985107,0.000455266,0.0001006578,0.0004934978,0.0003562318,0.00008356859],"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":[0.0004591346,0.0002433451,0.002302773,0.0001705994,0.00007577957,0.00009766538,0.00007911839,0.03868254,0.03229944,0.007961075,0.01880605,0.8988225],"study_design_scores_gemma":[0.00005335096,0.0002461957,0.0009757042,0.00004155064,0.00006110758,0.0002370852,0.00003412342,0.9292399,0.04019977,0.01851463,0.01036787,0.00002864677],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07193045,0.0009123369,0.8810847,0.0003223805,0.000558739,0.0001390276,0.0003886774,0.03640361,0.00825999],"genre_scores_gemma":[0.5486304,0.0003549208,0.4271642,0.0005183492,0.0002918096,0.0001550497,0.001476973,0.003051524,0.01835673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006815132,"threshold_uncertainty_score":0.0227989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01059401334469041,"score_gpt":0.2675288737085019,"score_spread":0.2569348603638115,"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."}}