{"id":"W4386239748","doi":"10.5281/zenodo.8292980","title":"GPTCloneBench: A comprehensive benchmark of semantic clones and cross-language clones using GPT-3 model and SemanticCloneBench","year":2023,"lang":"en","type":"paratext","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; Natural language processing; Artificial intelligence; Programming language; 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":[0.004913734,0.003133388,0.0009574289,0.003658929,0.001125992,0.002270189,0.004126628,0.00250011,0.003628862],"category_scores_gemma":[0.02291639,0.000684518,0.002055677,0.004014333,0.001530169,0.004301983,0.002771192,0.002640382,0.003412323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002344083,"about_ca_system_score_gemma":0.002881522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01640988,"about_ca_topic_score_gemma":0.01736511,"domain_scores_codex":[0.9923992,0.001767637,0.0008994348,0.001813486,0.002606078,0.0005141763],"domain_scores_gemma":[0.9829134,0.006698116,0.0009337769,0.003623665,0.005064076,0.0007669182],"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":[0.00239689,0.002096735,0.06178985,0.005652988,0.0007432072,0.00250228,0.002366627,0.1324066,0.03150665,0.01317666,0.3611874,0.3841741],"study_design_scores_gemma":[0.0007837862,0.002147009,0.03283019,0.0004773074,0.0003732088,0.001766095,0.001643493,0.6891165,0.07826836,0.01646724,0.1758187,0.000308108],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.5315303,0.005061243,0.1372604,0.00229751,0.001438251,0.001642224,0.0991841,0.1840402,0.03754591],"genre_scores_gemma":[0.4431131,0.001144498,0.1919342,0.001336706,0.0001306022,0.001471422,0.3351561,0.01391923,0.01179409],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01640988,"threshold_uncertainty_score":0.03262872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1774222207259452,"score_gpt":0.3884332775431876,"score_spread":0.2110110568172424,"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."}}