{"id":"W4416750780","doi":"10.1109/nca67271.2025.00028","title":"ProvSpider: A Robust and Universal Toolkit for Binary Provenance Analysis Using Deep Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; Queen's University; McGill University","funders":"","keywords":"Byte; Executable; Binary number; Deep learning; Source code; Convolutional neural network; Sliding window protocol; Key (lock); Reverse engineering","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":[0.001371141,0.001299423,0.0005870991,0.001564166,0.0005521888,0.00154674,0.003099427,0.0009455717,0.004118645],"category_scores_gemma":[0.007163114,0.0007786226,0.001348666,0.000837977,0.001091945,0.004105324,0.002960341,0.002818312,0.00223113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001425578,"about_ca_system_score_gemma":0.003317518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007126811,"about_ca_topic_score_gemma":0.0171244,"domain_scores_codex":[0.9990631,0.0001600782,0.00007163498,0.0002518299,0.0003533756,0.0001000384],"domain_scores_gemma":[0.9981681,0.0006347059,0.0002159267,0.0005344849,0.0003669347,0.00007971023],"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":[0.0007759878,0.0004388282,0.01339634,0.001386891,0.0003199782,0.0006089209,0.0004444979,0.2259774,0.02689409,0.05963964,0.07333832,0.5967791],"study_design_scores_gemma":[0.00003353172,0.00004282442,0.0005419576,0.00006934463,0.00002778181,0.0001128393,0.00003423843,0.9287856,0.01337535,0.04271575,0.01422744,0.00003324312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01352548,0.0005389037,0.8882645,0.000452083,0.0001217436,0.0001715669,0.002542864,0.09163799,0.002744914],"genre_scores_gemma":[0.2657189,0.0007775272,0.7028867,0.0008805649,0.00007884217,0.0004362181,0.01543047,0.006736125,0.00705466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007126811,"threshold_uncertainty_score":0.01417065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08045647335972747,"score_gpt":0.353894632414488,"score_spread":0.2734381590547605,"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."}}