{"id":"W6912845974","doi":"10.5281/zenodo.8259967","title":"GPTCloneBench: A comprehensive benchmark of semantic clones and cross-language clones using GPT-3 model and SemanticCloneBench","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Indian and Buddhist Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Benchmark (surveying); clone (Java method); Replication (statistics); Work (physics)","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":[0.003598823,0.003607298,0.001169375,0.003611067,0.001143491,0.002593624,0.004855682,0.002745091,0.009800067],"category_scores_gemma":[0.01757083,0.001178703,0.002466271,0.004886758,0.001273027,0.003825712,0.00275046,0.001924561,0.007277173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001739733,"about_ca_system_score_gemma":0.002784692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01138402,"about_ca_topic_score_gemma":0.009060259,"domain_scores_codex":[0.9937973,0.001055296,0.0006993113,0.0012175,0.002737844,0.0004927167],"domain_scores_gemma":[0.988932,0.00402849,0.000653016,0.003029927,0.002899856,0.0004566582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002642181,0.0009315078,0.01658577,0.006411279,0.0007350956,0.001496092,0.001289848,0.09053534,0.0490723,0.02593807,0.4908115,0.313551],"study_design_scores_gemma":[0.001289006,0.001367987,0.01125317,0.0006364469,0.0006343703,0.002086237,0.0007414658,0.3783206,0.1703567,0.03362973,0.3993378,0.0003465688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.1314989,0.003475867,0.2557703,0.0009937588,0.000927988,0.001271492,0.09247943,0.467146,0.04643638],"genre_scores_gemma":[0.187465,0.001265021,0.2822316,0.0007417279,0.00009645963,0.001343352,0.4391726,0.07355806,0.01412621],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01138402,"threshold_uncertainty_score":0.03278452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06495941616610891,"score_gpt":0.2758032140217657,"score_spread":0.2108437978556568,"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."}}