{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002328979,0.001087817,0.001205474,0.002065636,0.000478739,0.0021704,0.002147381,0.0013314,0.006721289],"category_scores_gemma":[0.01347191,0.0009774514,0.0007497822,0.001462903,0.0005996027,0.005897864,0.003463386,0.001217202,0.003870084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006398993,"about_ca_system_score_gemma":0.001026305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002125323,"about_ca_topic_score_gemma":0.002946844,"domain_scores_codex":[0.997977,0.0002339702,0.0001923405,0.0003785381,0.001013041,0.0002051363],"domain_scores_gemma":[0.9941812,0.002457621,0.0003803812,0.001852852,0.0008010444,0.0003268105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003112031,0.001151136,0.03319662,0.001037219,0.0002410752,0.002227836,0.0008151099,0.007467856,0.06981609,0.02134169,0.1177658,0.7418275],"study_design_scores_gemma":[0.0006976151,0.0007406936,0.01926862,0.000231384,0.0001995739,0.003427036,0.0003907393,0.571946,0.237408,0.02183442,0.1435785,0.0002772535],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05809349,0.0004239147,0.5673962,0.0005523525,0.0002391684,0.0004597434,0.001882351,0.3634864,0.007466387],"genre_scores_gemma":[0.5128679,0.0004615344,0.4368536,0.0007625793,0.0002017333,0.0005230134,0.007578344,0.02558791,0.01516332],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006721289,"threshold_uncertainty_score":0.02248496,"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."}}