{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002267457,0.0003219378,0.0004654799,0.0005091795,0.001833118,0.000767328,0.0003712337,0.0001314179,0.007507195],"category_scores_gemma":[0.0001241773,0.0003121608,0.00007182456,0.0001407998,0.001226656,0.0001616363,0.001042052,0.0002540496,0.0004456381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004302962,"about_ca_system_score_gemma":0.000006016916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006874484,"about_ca_topic_score_gemma":0.00007705736,"domain_scores_codex":[0.9982578,0.000124852,0.0003552408,0.0005241474,0.0003457189,0.0003922678],"domain_scores_gemma":[0.9988388,0.00004256162,0.0002731313,0.0003466541,0.0003882328,0.0001105961],"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":[0.0002174421,0.0004135321,0.000132944,0.006744486,0.001360612,0.000246408,0.1414688,0.0002375635,0.002307739,0.1047033,0.7257007,0.01646647],"study_design_scores_gemma":[0.0008302072,0.0001899531,0.0004231327,0.0006369419,0.0001418455,0.00009052387,0.005009799,0.00293976,0.00003711016,0.000339851,0.9887069,0.000653965],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1320487,0.005527109,0.0001497198,0.0002164354,0.000611899,0.001330441,0.002955551,0.002028576,0.8551316],"genre_scores_gemma":[0.6000099,0.004526807,0.00048439,0.0001940846,0.001427675,3.055564e-7,0.001512161,0.01637225,0.3754725],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4796591,"threshold_uncertainty_score":0.9999331,"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."}}