{"id":"W4393825970","doi":"10.5281/zenodo.8259987","title":"GPTCloneBench: A comprehensive benchmark of semantic clones and cross-language clones using GPT-3 model and SemanticCloneBench","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Benchmark (surveying); Computer science; Computational biology; Biology; Natural language processing; Programming language; Artificial intelligence; Geography; Cartography","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":[0.001951471,0.003860724,0.001491157,0.00585918,0.001407886,0.002338894,0.00435514,0.002872394,0.01616377],"category_scores_gemma":[0.01136228,0.0008871382,0.002666466,0.007377856,0.000831936,0.002287445,0.002846513,0.002426682,0.02365429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002299652,"about_ca_system_score_gemma":0.00400672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0420121,"about_ca_topic_score_gemma":0.05657408,"domain_scores_codex":[0.9967643,0.0005661575,0.0003973079,0.0009395586,0.0009952249,0.0003373872],"domain_scores_gemma":[0.9949526,0.001721826,0.0002784875,0.00143022,0.001217253,0.0003996358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003495772,0.0001361069,0.002482287,0.001320623,0.0001343862,0.0001429874,0.00009327487,0.004156331,0.001035992,0.001848787,0.9750117,0.01328798],"study_design_scores_gemma":[0.001115547,0.0001524956,0.00993083,0.0004826458,0.000199394,0.0004712524,0.0003347955,0.01638185,0.005592423,0.006340176,0.9588733,0.0001253567],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.004254006,0.0004156154,0.001535643,0.0002162489,0.00009845317,0.00007320034,0.9801055,0.01034979,0.0029517],"genre_scores_gemma":[0.00153839,0.00006534351,0.001569395,0.00005660432,0.000004616794,0.00007387054,0.9957808,0.0004627825,0.0004481372],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0420121,"threshold_uncertainty_score":0.08353513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1665359397910992,"score_gpt":0.3846994595654621,"score_spread":0.218163519774363,"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."}}