{"id":"W1984348519","doi":"10.1109/suite.2012.6225474","title":"Similarity search plug-in: Clone detection meets internet-scale code search","year":2012,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; The Internet; Nearest neighbor search; Scalability; Eclipse; Similarity (geometry); clone (Java method); Information retrieval; Source code; Plug-in; Code (set theory); Search engine; Open source; World Wide Web; Data mining; Database; Artificial intelligence; Software; Programming language; Set (abstract data type)","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":[0.001263121,0.0001100528,0.0001636548,0.0002262474,0.0000613892,0.000148843,0.0007223681,0.00007622591,0.00009425579],"category_scores_gemma":[0.00002610756,0.0000968102,0.00006365732,0.0006845007,0.0000425368,0.0008021133,0.0005224909,0.000268665,0.0002854967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007717282,"about_ca_system_score_gemma":0.00003032061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001590759,"about_ca_topic_score_gemma":0.001020296,"domain_scores_codex":[0.9983852,0.000166515,0.0001996603,0.0003533764,0.0003838245,0.0005114489],"domain_scores_gemma":[0.9990886,0.00008735072,0.00002192174,0.0005647483,0.00005607999,0.0001812819],"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":[0.00005405512,0.00138062,0.4503112,0.0001014492,0.0001662963,0.00004700632,0.01147906,0.0008390961,0.02415616,0.01130548,0.003981058,0.4961784],"study_design_scores_gemma":[0.0005662764,0.0001174735,0.1084062,0.00003272002,0.00001623919,0.00003268354,0.0002800532,0.7200679,0.161348,0.00009387491,0.008590079,0.0004484651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5146418,0.00007453159,0.4806022,0.0009745003,0.0001793059,0.00006496405,0.000003873412,0.0001458187,0.003313015],"genre_scores_gemma":[0.9839978,0.00001264074,0.01416195,0.0001398808,0.00009591212,0.000005177721,0.00000555269,0.000006756532,0.001574355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7192288,"threshold_uncertainty_score":0.3947805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04283692919118137,"score_gpt":0.2938351497241997,"score_spread":0.2509982205330183,"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."}}