{"id":"W2588556346","doi":"10.1142/s0218194016400106","title":"A Machine Learning Based Approach for Evaluating Clone Detection Tools for a Generalized and Accurate Precision","year":2016,"lang":"en","type":"article","venue":"International Journal of Software Engineering and Knowledge Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Generality; clone (Java method); Computer science; Measure (data warehouse); Machine learning; Software; Variety (cybernetics); Data mining; Artificial intelligence; Java; Sample (material); Detector; Algorithm; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001287829,0.000232851,0.0002888636,0.0005517117,0.00007114428,0.000271337,0.0004571225,0.00009628895,0.000001207686],"category_scores_gemma":[0.01166638,0.0001881644,0.0001268106,0.0001747129,0.00001391443,0.0007365068,0.0001372617,0.0002224363,4.006554e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001575475,"about_ca_system_score_gemma":0.0000702761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001428587,"about_ca_topic_score_gemma":2.095503e-7,"domain_scores_codex":[0.998577,0.0000262393,0.0004555566,0.0002994027,0.0003373948,0.0003044193],"domain_scores_gemma":[0.9945355,0.004331644,0.0001490576,0.00013411,0.0006900806,0.0001596275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002195872,0.00007268872,0.0008038593,0.000431642,0.0002970186,0.000009008965,0.0003752745,0.499034,0.07920756,0.0005211911,0.00002368075,0.4190045],"study_design_scores_gemma":[0.002416968,0.0003219532,0.001008455,0.0003437028,0.00002157321,0.0001164012,0.000003785747,0.9852061,0.008465482,0.00003250458,0.001818669,0.0002444143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05824419,0.001572274,0.9388314,0.00006318567,0.0008279997,0.0002502146,0.0000114318,0.0001984709,7.947042e-7],"genre_scores_gemma":[0.6050147,0.00007441946,0.3944792,0.000004189667,0.0002915185,0.00006699199,0.000003369167,0.00003746181,0.00002808819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5467706,"threshold_uncertainty_score":0.9966588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03570845271944944,"score_gpt":0.3056461376792703,"score_spread":0.2699376849598209,"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."}}