{"id":"W3013132080","doi":"10.1109/iwsc50091.2020.9047643","title":"SemanticCloneBench: A Semantic Code Clone Benchmark using Crowd-Source Knowledge","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Java; Benchmark (surveying); Programming language; clone (Java method); Python (programming language); Source code; Code (set theory)","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":[0.00532375,0.001793121,0.0009011672,0.007068262,0.00102847,0.001742149,0.002658015,0.001924685,0.00167087],"category_scores_gemma":[0.02827567,0.0004799757,0.001010617,0.003949529,0.001240339,0.003194816,0.003249182,0.001199944,0.001056895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001319544,"about_ca_system_score_gemma":0.00205577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006465557,"about_ca_topic_score_gemma":0.00733791,"domain_scores_codex":[0.9914874,0.002216885,0.0007661703,0.001661439,0.003447319,0.0004208503],"domain_scores_gemma":[0.9784468,0.008687181,0.001752367,0.00440685,0.00578453,0.0009222145],"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":[0.002303138,0.002797562,0.09880418,0.004069133,0.0009719004,0.002695098,0.008399706,0.1060357,0.08095278,0.01983229,0.0772583,0.5958802],"study_design_scores_gemma":[0.0005389556,0.001904325,0.0638722,0.0005284213,0.0003158434,0.001969638,0.00340184,0.685734,0.1305199,0.02219048,0.08858606,0.0004383679],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5541143,0.001099961,0.3438482,0.0005648478,0.000280779,0.002258647,0.01715002,0.06437067,0.01631256],"genre_scores_gemma":[0.5828739,0.000294773,0.3570458,0.0002513691,0.00005626952,0.001736709,0.04909072,0.004677354,0.003973095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007068262,"threshold_uncertainty_score":0.02815503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04975131297904765,"score_gpt":0.2908692215705029,"score_spread":0.2411179085914553,"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."}}