{"id":"W1972466226","doi":"10.5555/2662708.2662714","title":"Scaling classical clone detection tools for ultra-large datasets: an exploratory study","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Saskatchewan","funders":"","keywords":"Shuffling; Computer science; Scalability; Java; clone (Java method); Precision and recall; Cloning (programming); Data mining; Scaling; Machine learning; Artificial intelligence; Programming language; Database; Biology; Mathematics","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":[0.01971687,0.001302179,0.0008448894,0.004671608,0.001318663,0.002602761,0.002801135,0.00128088,0.0007415671],"category_scores_gemma":[0.08053191,0.00045523,0.001231922,0.00506848,0.001802652,0.005572741,0.003905087,0.002420673,0.0005190686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001326631,"about_ca_system_score_gemma":0.001253889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002801332,"about_ca_topic_score_gemma":0.003369915,"domain_scores_codex":[0.9804198,0.008309624,0.001933616,0.002932739,0.005540476,0.0008637473],"domain_scores_gemma":[0.8724886,0.08492332,0.006467116,0.02406334,0.01006621,0.001991445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002352144,0.007269272,0.3187124,0.002659065,0.001448106,0.001220604,0.004608115,0.06384504,0.06805839,0.006934652,0.04014085,0.4827514],"study_design_scores_gemma":[0.0007858631,0.004954597,0.184117,0.0003338477,0.0004253476,0.001890653,0.006075547,0.6942617,0.06889588,0.01385129,0.02411758,0.0002907884],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9399999,0.001039839,0.04662998,0.0008222428,0.0001468142,0.001067507,0.002970325,0.005141415,0.002181984],"genre_scores_gemma":[0.8367316,0.0003858086,0.1531448,0.0003007223,0.000111791,0.0008065779,0.007432532,0.000483862,0.0006023116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01971687,"threshold_uncertainty_score":0.104274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04949483932293088,"score_gpt":0.309086298293043,"score_spread":0.2595914589701122,"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."}}