{"id":"W2963174348","doi":"10.14778/2994509.2994534","title":"LSH ensemble","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Jaccard index; Computer science; Data mining; Domain (mathematical analysis); Locality-sensitive hashing; Data structure; Data set; Set (abstract data type); Hash function; Mathematics; Cluster analysis; Hash table; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000185335,0.00009858549,0.0001151825,0.00004465561,0.00006265881,0.00003412601,0.001077037,0.00002741466,0.000007321221],"category_scores_gemma":[0.0001139504,0.00004764201,0.00008073931,0.000247322,0.0000565943,0.0005505309,0.0005385869,0.00004971574,0.00001444116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005022846,"about_ca_system_score_gemma":0.00001560587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000370667,"about_ca_topic_score_gemma":1.579966e-7,"domain_scores_codex":[0.9991205,0.000003087012,0.0001775863,0.0002209275,0.0002731289,0.000204796],"domain_scores_gemma":[0.999418,0.00003544148,0.0001481641,0.0002022782,0.0001529271,0.00004322637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007125408,0.00004081479,0.0008684829,0.0000181603,0.00001025701,3.289275e-7,0.0001135073,6.117543e-8,0.678563,0.1562902,0.004964155,0.1591239],"study_design_scores_gemma":[0.0001654469,0.00006468075,0.0004327887,0.00007612592,0.00000323255,0.000007140899,0.000007675085,0.00001165163,0.9174836,0.06580421,0.01586788,0.00007553816],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04250883,0.0004496242,0.8830945,0.01294032,0.0005182425,0.0009562579,0.000004291896,0.0007452253,0.05878263],"genre_scores_gemma":[0.9593542,0.0001255179,0.03851346,0.0002420546,0.00003889057,0.00002536894,2.208931e-8,0.000007568619,0.001692888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9168454,"threshold_uncertainty_score":0.2001421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01131773862150246,"score_gpt":0.2360180883857376,"score_spread":0.2247003497642351,"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."}}