{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00147568,0.00126392,0.0009530717,0.005747862,0.0005605435,0.001596016,0.001950217,0.001375525,0.001022933],"category_scores_gemma":[0.008693219,0.0005534115,0.001473754,0.002194755,0.0007188483,0.002305316,0.001997672,0.001262885,0.001024823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113224,"about_ca_system_score_gemma":0.002073843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01220712,"about_ca_topic_score_gemma":0.01347217,"domain_scores_codex":[0.9978036,0.0002249552,0.0001926836,0.0006673223,0.0009704405,0.0001408713],"domain_scores_gemma":[0.9914927,0.002425941,0.002042728,0.001338794,0.002448344,0.0002515415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005731545,0.0006346379,0.1301445,0.000718561,0.000429712,0.0009767277,0.0008153358,0.02889148,0.0473181,0.003570007,0.01453264,0.7713952],"study_design_scores_gemma":[0.00007737099,0.0004376202,0.04192613,0.00009256572,0.0001749182,0.001252375,0.000212612,0.8703853,0.06506837,0.004923345,0.01532573,0.0001236526],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3286154,0.001346575,0.5846983,0.0004498632,0.0001321138,0.0006446114,0.003370221,0.07653163,0.004211341],"genre_scores_gemma":[0.7003262,0.000299186,0.2844229,0.0003296917,0.00003967899,0.000352416,0.007392905,0.0009699601,0.005867134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01220712,"threshold_uncertainty_score":0.02427214,"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."}}