{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006981416,0.0001230961,0.0001303725,0.0001157048,0.0001482658,0.000616856,0.0007635963,0.000055134,0.00003046475],"category_scores_gemma":[0.00101256,0.000108477,0.00003335797,0.0003034422,0.00001615471,0.002748039,0.0001522186,0.0001672731,0.0001538601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006137239,"about_ca_system_score_gemma":0.00003527098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002088612,"about_ca_topic_score_gemma":0.00003755884,"domain_scores_codex":[0.9984949,0.00007813185,0.0001952432,0.0004641947,0.0003500596,0.0004174214],"domain_scores_gemma":[0.9978603,0.00101059,0.00002342942,0.0008047234,0.000109107,0.000191846],"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":[0.00006399301,0.005124204,0.008274952,0.0001530083,0.0002026018,0.00004653587,0.006911634,0.001096801,0.1238468,0.005135705,0.02374214,0.8254016],"study_design_scores_gemma":[0.005846458,0.004357629,0.05722274,0.00004667719,0.00003023501,0.0000319078,0.005801992,0.7765983,0.1284692,0.001392959,0.01833904,0.001862902],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3357082,0.000008171744,0.6629707,0.00006429344,0.0001979498,0.0006091198,0.00001254817,0.0004215636,0.000007542016],"genre_scores_gemma":[0.9808382,0.00000102019,0.01844824,0.00007165084,0.0001192956,0.0004477653,0.00002705769,0.00001654758,0.00003024599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8235387,"threshold_uncertainty_score":0.5948356,"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."}}