{"id":"W2511803001","doi":"10.1145/2970276.2970326","title":"Deep learning code fragments for code clone detection","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":569,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Singapore Management University; University of Saskatchewan; National Science Foundation","keywords":"Computer science; Identifier; clone (Java method); Java; False positive paradox; Source code; Software maintenance; Code (set theory); Artificial intelligence; Software; Program comprehension; Point (geometry); Static program analysis; Software system; Programming language; Machine learning; Data mining; Software development; Set (abstract data type)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001368764,0.0009594557,0.0006788613,0.003139853,0.0004992947,0.0007911428,0.001759149,0.001171516,0.001072406],"category_scores_gemma":[0.009551055,0.000431241,0.0007028077,0.002056925,0.0006412547,0.002129784,0.001170673,0.001672535,0.0006410503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108474,"about_ca_system_score_gemma":0.001247029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006990434,"about_ca_topic_score_gemma":0.009760031,"domain_scores_codex":[0.998789,0.0001955341,0.00009328692,0.0003758384,0.0004351316,0.0001112805],"domain_scores_gemma":[0.9940262,0.002381301,0.001041397,0.0009434537,0.001411505,0.0001961392],"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":[0.0002973184,0.0003075144,0.03941726,0.0002376953,0.0001153345,0.0002801568,0.0003551177,0.09719716,0.02623928,0.00319296,0.006117604,0.8262427],"study_design_scores_gemma":[0.00001363797,0.000090111,0.004555907,0.00002722709,0.00003381951,0.0001540315,0.0000747449,0.9726956,0.01384675,0.006244814,0.002246901,0.00001645343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1981662,0.0008791715,0.7896443,0.0004270584,0.00005540449,0.0001583572,0.0008333558,0.008314299,0.001521753],"genre_scores_gemma":[0.636966,0.0002570652,0.3573798,0.0001654404,0.00003986958,0.0001447106,0.00286956,0.0002719908,0.001905569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006990434,"threshold_uncertainty_score":0.01389951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01918773439204367,"score_gpt":0.2735869598500928,"score_spread":0.2543992254580492,"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."}}