{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001940913,0.001017928,0.002086488,0.002299715,0.001130173,0.00142486,0.002814992,0.001649347,0.006213341],"category_scores_gemma":[0.009290032,0.0004235014,0.0009942448,0.00249552,0.0006770555,0.003554343,0.00305159,0.001580052,0.002750023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001120628,"about_ca_system_score_gemma":0.00150527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004156455,"about_ca_topic_score_gemma":0.00725128,"domain_scores_codex":[0.9979661,0.0004088411,0.00009223093,0.000509106,0.0008025373,0.0002212636],"domain_scores_gemma":[0.9961525,0.001461089,0.000194196,0.001197182,0.0007620837,0.0002329961],"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":[0.0002908639,0.0003285727,0.009156119,0.0002516903,0.000272901,0.0001637288,0.0002149887,0.3901968,0.004409726,0.02080715,0.02733235,0.5465751],"study_design_scores_gemma":[0.00001607834,0.00009887708,0.0006630596,0.00001396177,0.00002150712,0.0001257133,0.0000672997,0.9754544,0.002018864,0.01592452,0.005579961,0.00001567707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08015309,0.002521345,0.8994592,0.0008972928,0.0004385928,0.0003125258,0.002067504,0.004608433,0.009542054],"genre_scores_gemma":[0.4733479,0.0008565969,0.5023776,0.0009670212,0.0005542141,0.0004118701,0.007565315,0.0006200852,0.01329939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006213341,"threshold_uncertainty_score":0.02078569,"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."}}