{"id":"W2425458534","doi":"10.1145/2882903.2914838","title":"Searching Web Data using MinHash LSH","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Locality-sensitive hashing; Computer science; Search engine indexing; Index (typography); Information retrieval; Hash function; World Wide Web; Hash table; Computer security","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":[0.0003121328,0.00008004354,0.00008522515,0.00006588925,0.00008128089,0.0001001415,0.0016976,0.00002578339,0.00003786856],"category_scores_gemma":[0.0001348585,0.00004817866,0.00001986726,0.0002118789,0.00003927339,0.002166291,0.001571532,0.00005686081,0.00005650601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002634895,"about_ca_system_score_gemma":0.00006701427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001535954,"about_ca_topic_score_gemma":0.000003708057,"domain_scores_codex":[0.9990305,0.00003316617,0.0001241593,0.0003808173,0.0001914046,0.0002399951],"domain_scores_gemma":[0.998448,0.0001151508,0.0000342092,0.0012902,0.00004319067,0.00006922316],"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":[0.000002063719,0.00001703246,0.0001955411,0.000004438968,0.00000534322,0.00001974626,0.0000233903,3.84059e-7,0.1677684,0.02239571,0.00240517,0.8071628],"study_design_scores_gemma":[0.0006594258,0.0001253152,0.0002370818,0.0002189693,0.000007927603,0.0001090224,0.00001721904,0.1056413,0.6303797,0.04808129,0.2138397,0.0006830365],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002241264,0.0000592124,0.992363,0.0007085094,0.00006676224,0.00007050133,0.000004018621,0.0004230997,0.004063676],"genre_scores_gemma":[0.2418382,0.00006508511,0.7564167,0.0003323387,0.00007105603,9.667467e-7,0.000001001325,0.000008463788,0.001266192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8064798,"threshold_uncertainty_score":0.3154592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1440010960189437,"score_gpt":0.3833650304849872,"score_spread":0.2393639344660435,"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."}}