{"id":"W2967758098","doi":"10.1145/3338906.3341182","title":"CloneCognition: machine learning based code clone validation tool","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"clone (Java method); Computer science; Source code; Code (set theory); Generalization; Software maintenance; Programming language; Program comprehension; Software; Codebase; Software system; Process (computing); Artificial intelligence; Software engineering; Machine learning; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001898527,0.001560004,0.0008059327,0.003337286,0.0005933897,0.001273256,0.0029751,0.002102836,0.004689552],"category_scores_gemma":[0.01461049,0.0007033706,0.001181885,0.001231657,0.0008305325,0.00246703,0.00180496,0.001922761,0.002986886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007661475,"about_ca_system_score_gemma":0.001461058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002758462,"about_ca_topic_score_gemma":0.003031985,"domain_scores_codex":[0.9978722,0.0003202437,0.0001900561,0.0006338219,0.0008572356,0.0001264106],"domain_scores_gemma":[0.9932542,0.003826972,0.0007429561,0.0009298455,0.001093829,0.0001520897],"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":[0.0005934171,0.0004140653,0.01850221,0.001044581,0.0002617159,0.001155311,0.0006719086,0.02870508,0.04091929,0.006359803,0.09777336,0.8035994],"study_design_scores_gemma":[0.0001714797,0.0002926582,0.007475059,0.0002322162,0.00009984207,0.001567881,0.0001706152,0.7999663,0.1176423,0.01177507,0.06045088,0.0001556288],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02639357,0.0006541056,0.6146498,0.0003370279,0.0001909336,0.0003438168,0.002328241,0.3524464,0.002656067],"genre_scores_gemma":[0.2361148,0.0004369955,0.7303419,0.0007274958,0.00008219555,0.0007833675,0.01243207,0.0119985,0.007082683],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004689552,"threshold_uncertainty_score":0.01568806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768197075489549,"score_gpt":0.2522891837512765,"score_spread":0.234607212996381,"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."}}