{"id":"W4383215759","doi":"10.1016/j.jss.2023.111796","title":"A systematic literature review on source code similarity measurement and clone detection: Techniques, applications, and challenges","year":2023,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Source code; Code review; Field (mathematics); Similarity (geometry); Software; Code (set theory); Java; Software engineering; Static program analysis; Software development; Point (geometry); Data mining; Information retrieval; Programming language; Artificial intelligence","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":[0.002835246,0.0001352403,0.000423187,0.0002259711,0.0001191045,0.0002112096,0.0002181609,0.00008401378,1.319507e-7],"category_scores_gemma":[0.0007518758,0.00009922778,0.00004002389,0.000364541,0.00002205705,0.0001877982,0.0001010798,0.0002814654,0.000001248451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006047509,"about_ca_system_score_gemma":0.00002870488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001906058,"about_ca_topic_score_gemma":0.00000121388,"domain_scores_codex":[0.9984381,0.0001466975,0.0004292215,0.0002132946,0.0006206217,0.0001520985],"domain_scores_gemma":[0.9985219,0.0004122759,0.0002222559,0.0002989149,0.0003999375,0.0001446781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00002233629,0.0001046447,0.00112153,0.8116004,0.0003507547,0.0002644609,0.002012109,0.00006525601,0.000345023,0.001324862,0.002204921,0.1805837],"study_design_scores_gemma":[0.001585347,0.002088532,0.01534266,0.8775161,0.0002715587,0.01344939,0.0006166383,0.004827449,0.0004493759,0.0007615258,0.0817548,0.001336645],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000887493,0.7995825,0.1971985,0.001102884,0.0001232572,0.0008651486,0.000003585736,0.0002332441,0.000003313875],"genre_scores_gemma":[0.2127594,0.7801232,0.006089524,0.000161186,0.0003661718,0.0003663775,9.185571e-7,0.00004024338,0.00009294556],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2118719,"threshold_uncertainty_score":0.4046391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04170936095502379,"score_gpt":0.2713537760964991,"score_spread":0.2296444151414753,"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."}}