{"id":"W4393455678","doi":"10.5281/zenodo.8259988","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; Natural language processing; Computational biology; Artificial intelligence; Linguistics; Biology; Geography; Philosophy; 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":[0.00186509,0.003809097,0.001523192,0.005528048,0.001578984,0.002308109,0.004465043,0.002994303,0.0118598],"category_scores_gemma":[0.01046931,0.0008097825,0.002663688,0.007178071,0.0009096577,0.00233761,0.002823374,0.002385709,0.0164473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002619362,"about_ca_system_score_gemma":0.004130148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04953465,"about_ca_topic_score_gemma":0.06759237,"domain_scores_codex":[0.9966891,0.0005665706,0.0003987456,0.0009728638,0.001011873,0.0003608668],"domain_scores_gemma":[0.9951681,0.001488423,0.0002710676,0.001418364,0.00123152,0.0004225289],"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":[0.0004367822,0.0001729887,0.003336512,0.001377103,0.0001642982,0.0001813161,0.0001140713,0.004925021,0.00138832,0.002335927,0.9698444,0.01572327],"study_design_scores_gemma":[0.001169649,0.0001879216,0.01236083,0.0004609225,0.0002350127,0.0006241412,0.0004252247,0.02167246,0.006852165,0.006818646,0.9490622,0.0001308613],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00717133,0.0005735097,0.00186645,0.0003070062,0.0001251895,0.00009305315,0.975908,0.01040822,0.003547321],"genre_scores_gemma":[0.002131479,0.00007018044,0.0017939,0.00006386913,0.000005427798,0.00007350864,0.9949857,0.0003764156,0.0004995356],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04953465,"threshold_uncertainty_score":0.09849262,"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."}}