{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001544244,0.0009448535,0.0007995687,0.001104891,0.0006092637,0.002955239,0.002125946,0.001031741,0.02881169],"category_scores_gemma":[0.01121699,0.000626753,0.0007596615,0.002138939,0.001532203,0.006907151,0.003078165,0.001966356,0.009032013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001313788,"about_ca_system_score_gemma":0.001463202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001375351,"about_ca_topic_score_gemma":0.001819378,"domain_scores_codex":[0.9980782,0.0003161358,0.0001505411,0.0002825932,0.001012422,0.0001601603],"domain_scores_gemma":[0.9951048,0.00158057,0.0002280023,0.00219766,0.0007196919,0.0001692575],"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":[0.001524206,0.0001963179,0.001687883,0.0008150456,0.00007431553,0.0003334279,0.0005634269,0.04698244,0.02124576,0.2036715,0.08078407,0.6421215],"study_design_scores_gemma":[0.0002385501,0.0003485919,0.0008850994,0.0001652282,0.00003926903,0.0006426427,0.0002030769,0.5396723,0.0414966,0.3158114,0.1003896,0.0001077106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01395724,0.001025046,0.9558577,0.0008543467,0.0004433755,0.0001928679,0.001798449,0.01734455,0.0085265],"genre_scores_gemma":[0.2592805,0.0009498848,0.7124198,0.00122297,0.0005637383,0.0006884776,0.004267706,0.003625263,0.01698163],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02881169,"threshold_uncertainty_score":0.0963847,"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."}}