{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02879461,0.001494314,0.008008717,0.03260463,0.001371843,0.004316093,0.003259878,0.002727677,0.002413562],"category_scores_gemma":[0.1300244,0.00133173,0.006029694,0.02077083,0.002022477,0.005894801,0.003454824,0.001944807,0.0004449626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004059293,"about_ca_system_score_gemma":0.03123831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007747435,"about_ca_topic_score_gemma":0.0300064,"domain_scores_codex":[0.977091,0.006885246,0.009138462,0.002079069,0.004375776,0.0004304402],"domain_scores_gemma":[0.8377432,0.1243282,0.01797962,0.003045959,0.01543886,0.001464171],"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":[0.0002235421,0.00005187228,0.003461143,0.8146264,0.00456561,0.0001641264,0.0008315894,0.000161724,0.0005535056,0.0008271691,0.003625625,0.1709077],"study_design_scores_gemma":[0.0001242423,0.0003665219,0.00803481,0.9133542,0.03365662,0.0006773888,0.00106282,0.0002005161,0.0005379321,0.001261608,0.04064433,0.00007897698],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002093606,0.9951308,0.000870678,0.0007301429,0.0001550687,0.0002717415,0.0004383943,0.00001835894,0.0002911188],"genre_scores_gemma":[0.01880752,0.9738863,0.004464766,0.001253924,0.0001713837,0.0006410065,0.0006332624,0.00001816715,0.0001238479],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.03260463,"threshold_uncertainty_score":0.1522823,"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."}}