{"id":"W2901830053","doi":"10.1109/scam.2018.00025","title":"[Research Paper] On the Use of Machine Learning Techniques Towards the Design of Cloud Based Automatic Code Clone Validation Tools","year":2018,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"clone (Java method); Computer science; Maintainability; Software maintenance; Source code; Software system; Programming language; Software; Code (set theory); Machine learning; Software engineering; Artificial intelligence; Data mining","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":[0.00534048,0.0001110794,0.0001523494,0.0002008,0.0001891624,0.000186755,0.001331942,0.00005969139,0.0001424923],"category_scores_gemma":[0.006038386,0.00005936471,0.0000482883,0.0009901344,0.0002684002,0.0002812092,0.00031667,0.0004037306,0.00002327198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005832679,"about_ca_system_score_gemma":0.0001644944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002158519,"about_ca_topic_score_gemma":0.000003283813,"domain_scores_codex":[0.9970633,0.001048372,0.0002767726,0.0002319575,0.00107898,0.000300626],"domain_scores_gemma":[0.987662,0.01077171,0.00007661647,0.0009440702,0.000503256,0.00004237608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002198226,0.0008737223,0.005110004,0.0004573732,0.0002535179,0.00001752336,0.00539865,0.06048954,0.2721921,0.1100181,0.02066844,0.5243012],"study_design_scores_gemma":[0.00007601977,0.0004998836,0.002148092,0.00006564223,0.000002236569,0.000001360191,0.00001213928,0.5917219,0.4042574,0.0002604284,0.0008913554,0.00006358238],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04714435,0.00001228954,0.949793,0.001918805,0.00005666821,0.0006233411,0.000002706389,0.0003188715,0.0001299726],"genre_scores_gemma":[0.8616962,0.000008366098,0.1378902,0.0001107003,0.00004503657,0.0000604979,0.000001529841,0.00001496974,0.0001724665],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8145519,"threshold_uncertainty_score":0.7228948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2105035792821233,"score_gpt":0.3546240510437641,"score_spread":0.1441204717616408,"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."}}