{"id":"W2796141603","doi":"10.1109/saner.2018.8330194","title":"Benchmarks for software clone detection: A ten-year retrospective","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Saskatchewan","funders":"","keywords":"clone (Java method); Benchmark (surveying); Java; Computer science; Source lines of code; Software maintenance; Cloning (programming); Software; Software engineering; Precision and recall; Code refactoring; Set (abstract data type); Empirical research; Source code; Code (set theory); Software system; Programming language; Machine learning; Statistics; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0003057899,0.0001104772,0.0001185006,0.0001285468,0.0001701581,0.0001277144,0.0006155953,0.00007564866,0.000154675],"category_scores_gemma":[0.001283879,0.00009993112,0.000063117,0.0005443954,0.00006626108,0.0002866534,0.0002165374,0.0001323846,0.0001213935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001290828,"about_ca_system_score_gemma":0.00005426546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002561528,"about_ca_topic_score_gemma":0.0000208524,"domain_scores_codex":[0.9987832,0.00001452473,0.0001208883,0.0004194098,0.0002936212,0.0003683518],"domain_scores_gemma":[0.9985439,0.0003747496,0.00002344789,0.0005637418,0.000386722,0.0001074711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002940582,0.0005491144,0.3352524,0.0002743687,0.0004840633,0.00006040262,0.004152499,0.0001426962,0.009564293,0.1259037,0.1429058,0.3804166],"study_design_scores_gemma":[0.003431492,0.005129054,0.6771107,0.00008478513,0.00002138069,0.0001285481,0.0001110445,0.06783841,0.1770422,0.03317029,0.03423814,0.001693904],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0140319,0.00001852565,0.9833046,0.0002076845,0.0006275857,0.0002748819,0.000002705277,0.0006432952,0.0008888755],"genre_scores_gemma":[0.751565,0.000001396199,0.2470588,0.00006625219,0.000394255,0.00007076898,0.000001425137,0.00001314146,0.0008288694],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7375332,"threshold_uncertainty_score":0.4075073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01173961851561382,"score_gpt":0.2597864749169241,"score_spread":0.2480468564013102,"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."}}