{"id":"W1993673250","doi":"10.1109/saner.2015.7081830","title":"Threshold-free code clone detection for a large-scale heterogeneous Java repository","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"clone (Java method); Java; Granularity; Computer science; Benchmark (surveying); Source code; Code (set theory); Data mining; Software; Variety (cybernetics); Algorithm; Artificial intelligence; Operating system; Programming language; Biology","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":[0.002834565,0.0008390485,0.001306127,0.005196423,0.001131882,0.001550156,0.002599908,0.001595566,0.0003079791],"category_scores_gemma":[0.01968499,0.0004442057,0.001144004,0.003606977,0.0007415487,0.002520254,0.001686179,0.001016918,0.0003291329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001140232,"about_ca_system_score_gemma":0.001331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005267264,"about_ca_topic_score_gemma":0.00695559,"domain_scores_codex":[0.9955559,0.000579525,0.0004552363,0.001395026,0.001753144,0.0002611349],"domain_scores_gemma":[0.981768,0.006210736,0.003456235,0.003303411,0.004586378,0.0006752803],"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":[0.0006018741,0.0007166192,0.1423146,0.0004695969,0.0004049429,0.001074542,0.001100383,0.09451389,0.1212872,0.002539072,0.004638421,0.6303388],"study_design_scores_gemma":[0.0000355617,0.0002202506,0.02727455,0.00002091426,0.00007870889,0.000919533,0.0002576783,0.9178479,0.04833886,0.003526966,0.001418603,0.00006051787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4234768,0.0004508459,0.5640604,0.0001935732,0.00004404992,0.0001954642,0.000343898,0.01061167,0.0006231539],"genre_scores_gemma":[0.6945908,0.00009185295,0.3034626,0.00006962573,0.00001721904,0.0001218399,0.0008614311,0.000228594,0.000555972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005267264,"threshold_uncertainty_score":0.01499075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02652208983493504,"score_gpt":0.2673020073773731,"score_spread":0.240779917542438,"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."}}