{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001113742,0.002119087,0.002442063,0.004351909,0.001374505,0.001741198,0.004947162,0.002251134,0.0126803],"category_scores_gemma":[0.007852188,0.0011865,0.001723637,0.005251476,0.001068373,0.006023781,0.004987761,0.001473791,0.005087618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044333,"about_ca_system_score_gemma":0.002056101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006743291,"about_ca_topic_score_gemma":0.01110688,"domain_scores_codex":[0.9976127,0.0002756218,0.0001619171,0.0005900507,0.001131848,0.0002278928],"domain_scores_gemma":[0.9965239,0.00109207,0.0002657688,0.001393206,0.0005325009,0.0001925079],"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":[0.001287952,0.0003732062,0.004920732,0.0007390772,0.000362257,0.0004642154,0.0004969587,0.01009081,0.03836161,0.01214229,0.06712729,0.8636335],"study_design_scores_gemma":[0.0008491317,0.0007969994,0.003946506,0.0001306561,0.0002689686,0.001157128,0.0005303647,0.8040138,0.08429966,0.05982421,0.04399297,0.000189455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06183756,0.001607503,0.7144258,0.000279528,0.0003068591,0.000410419,0.002532325,0.2140526,0.004547363],"genre_scores_gemma":[0.2432103,0.000523484,0.7217562,0.0002688317,0.0001298876,0.0004567759,0.01102445,0.01278927,0.00984081],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0126803,"threshold_uncertainty_score":0.04241979,"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."}}