{"id":"W2043140003","doi":"10.1016/j.scico.2013.10.006","title":"SeByte: Scalable clone and similarity search for bytecode","year":2013,"lang":"en","type":"article","venue":"Science of Computer Programming","topic":"Software Engineering Research","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; University of Saskatchewan; Queen's University","funders":"","keywords":"Computer science; Bytecode; Scalability; Java bytecode; Ranking (information retrieval); Data mining; Similarity (geometry); Nearest neighbor search; Jaccard index; Source code; Matching (statistics); Heuristic; Binary search algorithm; Information retrieval; Theoretical computer science; Java; Search algorithm; Artificial intelligence; Programming language; Database; Pattern recognition (psychology); Java applet; Java annotation","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001715463,0.0001369311,0.0001978729,0.0003176444,0.0002772511,0.0007361175,0.001624662,0.00004927019,0.000004207934],"category_scores_gemma":[0.0001781846,0.0001268562,0.00004630935,0.001275346,0.0005608539,0.001327069,0.001064458,0.00016519,0.000009920574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004994163,"about_ca_system_score_gemma":0.000205329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008079565,"about_ca_topic_score_gemma":8.241246e-7,"domain_scores_codex":[0.9976519,0.00002579452,0.0002373007,0.0006048331,0.0007069953,0.00077317],"domain_scores_gemma":[0.9980645,0.000483919,0.00004933594,0.0005853522,0.0005552945,0.0002616521],"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":[0.000002801006,0.00009580452,0.01002668,0.0001818514,0.00001078342,0.000001917308,0.0006559145,0.0008487935,0.006248531,0.00839759,0.0003118396,0.9732175],"study_design_scores_gemma":[0.0004954448,0.0004353793,0.0356931,0.00007277427,0.00000288208,0.00002411595,0.0000255133,0.9269174,0.03297577,0.001915914,0.001119107,0.000322564],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2675374,0.00007294041,0.7309523,0.0004585568,0.0002012544,0.0005842328,6.561175e-7,0.000173227,0.00001947103],"genre_scores_gemma":[0.4869888,0.000002531417,0.5128692,0.00002197698,0.00004113102,0.00004869181,3.70396e-7,0.00000631466,0.00002097865],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9728949,"threshold_uncertainty_score":0.7098398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0207267550115444,"score_gpt":0.28171656020423,"score_spread":0.2609898051926856,"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."}}