{"id":"W4389544307","doi":"10.1109/icsme58846.2023.00013","title":"GPTCloneBench: A comprehensive benchmark of semantic clones and cross-language clones using GPT-3 model and SemanticCloneBench","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmark (surveying); Computer science; Natural language processing; Artificial intelligence; Programming language; Computational biology; Biology; Geography; Cartography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003422774,0.002812269,0.0009102265,0.004453673,0.001160991,0.001905475,0.005158052,0.002366969,0.002393652],"category_scores_gemma":[0.01633362,0.0007261923,0.001937186,0.005616666,0.001430543,0.003355535,0.002970797,0.002297535,0.001902179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002331959,"about_ca_system_score_gemma":0.002751862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01745941,"about_ca_topic_score_gemma":0.02210385,"domain_scores_codex":[0.9944482,0.0009770619,0.0005281436,0.001488124,0.002142866,0.0004156931],"domain_scores_gemma":[0.9890578,0.00422078,0.0007156795,0.002802684,0.002617116,0.0005859333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002129534,0.002416191,0.06214028,0.00469626,0.0008227518,0.002312882,0.001385031,0.2131547,0.02733006,0.013567,0.3700409,0.3000044],"study_design_scores_gemma":[0.000737607,0.001728261,0.03740945,0.0004119029,0.0003090472,0.001936673,0.001225775,0.6931381,0.06601067,0.01542271,0.1814322,0.0002376604],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5758634,0.004085036,0.1046532,0.0020197,0.0007690042,0.001361386,0.1631117,0.1157007,0.03243593],"genre_scores_gemma":[0.3117329,0.0009348352,0.1508143,0.0008173997,0.00006393837,0.001173969,0.5213991,0.007341858,0.00572175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01745941,"threshold_uncertainty_score":0.03471559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03741457056263726,"score_gpt":0.3245508019763634,"score_spread":0.2871362314137262,"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."}}