{"id":"W3000135256","doi":"10.1109/ase.2019.00099","title":"CLCDSA: Cross Language Code Clone Detection using Syntactical Features and API Documentation","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Source code; Programming language; Compiler; Software; Software maintenance; clone (Java method); Artificial intelligence; Natural language processing; Software development","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":[0.0001893773,0.00006947582,0.00007070656,0.00007855898,0.00005502038,0.0003466175,0.0001574939,0.00005053161,0.00002734728],"category_scores_gemma":[0.0001323045,0.00006269005,0.00001667172,0.0001822359,0.00001804739,0.0006125,0.0001321126,0.0001332792,0.00004956805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006239997,"about_ca_system_score_gemma":0.00001543829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000181465,"about_ca_topic_score_gemma":0.00001360671,"domain_scores_codex":[0.9992487,0.00002583536,0.00007776413,0.0002374033,0.0002283393,0.0001819307],"domain_scores_gemma":[0.9993798,0.0002829782,0.00001616479,0.000227408,0.00003394791,0.00005969504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00009706222,0.0001223796,0.2050675,0.0003041822,0.0001085131,0.0001279437,0.004131791,0.006553614,0.6962055,0.01354862,0.0002645188,0.07346833],"study_design_scores_gemma":[0.0009868804,0.0001755136,0.462163,0.00003340694,0.00000773037,0.0004037254,0.0001669265,0.2096086,0.3256194,0.0002815678,0.0001645836,0.0003887498],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7122586,0.00006061193,0.2871074,0.00005045798,0.0001820124,0.0000902054,4.027354e-7,0.0001567778,0.00009352595],"genre_scores_gemma":[0.9784642,0.000003581699,0.02094246,0.00004151514,0.00003759248,0.000003122681,6.658369e-7,0.000007391414,0.000499487],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3705862,"threshold_uncertainty_score":0.3342441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01163192908388964,"score_gpt":0.3243410991509543,"score_spread":0.3127091700670647,"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."}}