{"id":"W4385285635","doi":"10.1109/icde55515.2023.00367","title":"HyperMinHash: MinHash in LogLog Space (Extended Abstract)","year":2023,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Space (punctuation); Operating system","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003970315,0.0001099874,0.000172435,0.0003281395,0.0000513443,0.0001297668,0.0008031786,0.00005526333,0.0000957169],"category_scores_gemma":[0.00007681924,0.00009588423,0.0000617585,0.001502227,0.00002744353,0.0002751089,0.0002892926,0.0001126525,0.002034535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002030403,"about_ca_system_score_gemma":0.00005046111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001871773,"about_ca_topic_score_gemma":0.0001577301,"domain_scores_codex":[0.9988026,0.00002255854,0.000201903,0.000412169,0.0002165099,0.0003442732],"domain_scores_gemma":[0.9991081,0.0001153759,0.00004030222,0.0006305906,0.00002378805,0.00008185797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001291176,0.000486464,0.02528071,0.00007669257,0.0001360857,0.002636393,0.003233029,0.001459228,0.01886073,0.1609001,0.3024217,0.4844959],"study_design_scores_gemma":[0.001997347,0.0001715395,0.5430304,0.0001316026,0.00003511855,0.00009393838,0.001131592,0.367765,0.01227903,0.01326045,0.05840426,0.001699663],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.859932,0.00009162763,0.03247534,0.01178687,0.0005867353,0.0001652492,0.00001451343,0.001738736,0.0932089],"genre_scores_gemma":[0.9817169,0.00002227608,0.008279309,0.0002252133,0.00004011853,0.000007130228,0.00001580256,0.000006901616,0.009686351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5177497,"threshold_uncertainty_score":0.9987425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02480751285339491,"score_gpt":0.2683701622410557,"score_spread":0.2435626493876608,"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."}}