{"id":"W4384159091","doi":"10.1109/icpc58990.2023.00031","title":"Pathways to Leverage Transcompiler based Data Augmentation for Cross-Language Clone Detection","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; clone (Java method); Leverage (statistics); Source code; Exploit; Programming language; Software; Artificial intelligence","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":[0.001811024,0.001841662,0.0008212743,0.001481824,0.0006084695,0.001418774,0.002379825,0.001547146,0.003491145],"category_scores_gemma":[0.01122989,0.0006596992,0.001359699,0.001251924,0.0009737891,0.004098872,0.002978649,0.003114989,0.002774656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007718274,"about_ca_system_score_gemma":0.00155072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003558811,"about_ca_topic_score_gemma":0.005843483,"domain_scores_codex":[0.9984491,0.0003254873,0.0001013741,0.0006734994,0.0003380922,0.0001123934],"domain_scores_gemma":[0.9950057,0.001424851,0.0003908699,0.001620141,0.001379671,0.0001788209],"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":[0.001016547,0.0006506079,0.02277073,0.000640951,0.0002767579,0.001052274,0.001013748,0.07953262,0.09414008,0.007613376,0.01940947,0.7718829],"study_design_scores_gemma":[0.00006973615,0.0003177097,0.003033444,0.00009968125,0.0001250971,0.0006352307,0.0002316233,0.846821,0.1048924,0.02106682,0.02261933,0.0000880017],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1040908,0.001577662,0.8481619,0.001594072,0.0005249716,0.0002528808,0.002801952,0.03645603,0.004539731],"genre_scores_gemma":[0.42292,0.0006292138,0.5543224,0.001401334,0.0001184686,0.0005017433,0.0106323,0.002512393,0.006961999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003558811,"threshold_uncertainty_score":0.01167899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09413039926532048,"score_gpt":0.3641596172484101,"score_spread":0.2700292179830897,"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."}}