{"id":"W4377103668","doi":"10.1145/3592623","title":"Asm2Seq: Explainable Assembly Code Functional Summary Generation for Reverse Engineering and Vulnerability Analysis","year":2023,"lang":"en","type":"article","venue":"Digital Threats Research and Practice","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; Queen's University","funders":"","keywords":"Computer science; Reverse engineering; Firmware; Source code; Assembly language; Automatic summarization; Vulnerability (computing); Code review; Code (set theory); Static program analysis; Leverage (statistics); Software; Process (computing); Context (archaeology); Software engineering; Artificial intelligence; Programming language; Software development; Computer security; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001164853,0.002462589,0.0006603137,0.002935052,0.0005642287,0.0009635,0.001809518,0.001355414,0.009511383],"category_scores_gemma":[0.007586551,0.0004981758,0.001332217,0.001302213,0.0004584151,0.001707744,0.001648602,0.001407779,0.005161437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007660277,"about_ca_system_score_gemma":0.001455237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004723047,"about_ca_topic_score_gemma":0.0102873,"domain_scores_codex":[0.998908,0.0002539388,0.00009086213,0.0003868913,0.0002837973,0.00007646646],"domain_scores_gemma":[0.9966272,0.001412209,0.0002698577,0.0008131506,0.0007804564,0.0000972435],"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":[0.0007554044,0.0003579831,0.007751052,0.001446892,0.0002066531,0.0009377408,0.0008265367,0.02903477,0.04129833,0.006006016,0.1515334,0.7598452],"study_design_scores_gemma":[0.0002555966,0.0005678038,0.007251113,0.0001398998,0.0001738457,0.00100199,0.0004095605,0.7718201,0.08632068,0.02059107,0.1113254,0.0001429465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04095696,0.001089016,0.7277815,0.0007027944,0.0003774508,0.0007320956,0.03056679,0.1937609,0.004032506],"genre_scores_gemma":[0.138888,0.0003826679,0.7541704,0.000404643,0.0001352341,0.0008820167,0.09349472,0.005872436,0.005769968],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009511383,"threshold_uncertainty_score":0.03181875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1742418370316224,"score_gpt":0.3943273732383624,"score_spread":0.22008553620674,"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."}}