{"id":"W1512615396","doi":"10.1002/smr.1662","title":"Big data clone detection using classical detectors: an exploratory study","year":2014,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Saskatchewan","funders":"","keywords":"Computer science; Scalability; Big data; Source code; Code (set theory); clone (Java method); Data mining; Data science; Database; 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":[],"consensus_categories":[],"category_scores_codex":[0.001760865,0.0001382423,0.0002200881,0.0003354233,0.000185626,0.0001927972,0.0009694026,0.00007914333,0.000001483915],"category_scores_gemma":[0.002004125,0.0001206484,0.00002791624,0.0005556226,0.0000497822,0.001882889,0.0002701437,0.0003969536,0.000002228476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001107066,"about_ca_system_score_gemma":0.000205091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008251694,"about_ca_topic_score_gemma":0.00002821797,"domain_scores_codex":[0.9982194,0.0002117766,0.0003654913,0.0003241754,0.0006463953,0.0002327209],"domain_scores_gemma":[0.9982025,0.0003226396,0.0002167222,0.0005498567,0.0004639298,0.0002443583],"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":[0.0002772579,0.001531237,0.3162011,0.0003874601,0.0001909024,0.00009488054,0.006839851,0.005284089,0.004636635,0.00007930971,0.0001864702,0.6642908],"study_design_scores_gemma":[0.00515132,0.00680423,0.3875199,0.0004250896,0.0001538997,0.0015083,0.002287602,0.5865827,0.002628135,0.003665281,0.001969276,0.0013043],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4758369,0.000163625,0.5233446,0.00001738586,0.0005081526,0.00005685613,7.688791e-7,0.00007137821,3.763544e-7],"genre_scores_gemma":[0.9888951,0.000006376227,0.01030041,0.00001715497,0.0007593828,0.000002475196,6.121635e-7,0.00001526813,0.000003233503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6629865,"threshold_uncertainty_score":0.4919899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07457598398553884,"score_gpt":0.3182856481568901,"score_spread":0.2437096641713513,"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."}}