{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005507749,0.0001048435,0.0002285488,0.0002350944,0.0002044402,0.0001708355,0.0002283131,0.00007816114,8.608562e-7],"category_scores_gemma":[0.0002165242,0.00009244885,0.00005308269,0.0002832092,0.00001858415,0.0008657415,0.0001199472,0.0002450762,5.879397e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006627039,"about_ca_system_score_gemma":0.00005168054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000167506,"about_ca_topic_score_gemma":7.536277e-7,"domain_scores_codex":[0.9989822,0.00004843487,0.0004774982,0.0001525948,0.0001934424,0.0001458361],"domain_scores_gemma":[0.9989265,0.0001635962,0.0004609716,0.0001448306,0.0002444253,0.00005965514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003000311,0.0002450465,0.05205205,0.002722778,0.0005289549,0.0004312789,0.004609899,0.009507568,0.06324957,0.01440483,0.1119949,0.7399531],"study_design_scores_gemma":[0.005516088,0.005150612,0.01069799,0.01905063,0.0002786244,0.004875336,0.005916997,0.2008741,0.02938751,0.01714824,0.698524,0.00257985],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03132877,0.005049623,0.9622622,0.0001196781,0.0009448528,0.00007248832,0.000001991599,0.0001644133,0.0000560235],"genre_scores_gemma":[0.9412224,0.0001979897,0.05772023,0.0002405963,0.0001362305,0.000006394771,6.241047e-7,0.00001105625,0.0004645291],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9098936,"threshold_uncertainty_score":0.3769955,"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."}}