{"id":"W2796436043","doi":"10.1109/tkde.2020.2981311","title":"HyperMinHash: MinHash in LogLog space","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Jaccard index; Cardinality (data modeling); Combinatorics; Mathematics; Discrete mathematics; Computer science; Data mining; Statistics","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":[0.00141678,0.001027312,0.0008762989,0.00109969,0.0006775057,0.003138729,0.00236129,0.001222339,0.02493601],"category_scores_gemma":[0.01353969,0.0005730311,0.0006214766,0.002123513,0.001346093,0.00616884,0.003356775,0.002199578,0.008965727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201957,"about_ca_system_score_gemma":0.001945809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001304067,"about_ca_topic_score_gemma":0.001947902,"domain_scores_codex":[0.9978259,0.0003516382,0.0001632684,0.0003498571,0.001120261,0.0001889154],"domain_scores_gemma":[0.9946893,0.001745037,0.000201273,0.002575441,0.000593135,0.0001958705],"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":[0.001503604,0.0002324423,0.001560964,0.000853671,0.00007964441,0.0002959715,0.0005946997,0.04870079,0.02199268,0.1658984,0.07646733,0.6818199],"study_design_scores_gemma":[0.0002831931,0.0003430358,0.0006169669,0.000211554,0.00004354723,0.0006967098,0.0002931305,0.5961723,0.0496827,0.2395857,0.1119582,0.0001128846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01928549,0.001472497,0.9342111,0.001129239,0.0005660467,0.0002960078,0.002407563,0.02819676,0.01243535],"genre_scores_gemma":[0.2833791,0.001175353,0.6874025,0.001502579,0.0005160156,0.0007476658,0.004372739,0.0049659,0.01593807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02493601,"threshold_uncertainty_score":0.08341932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04477670225587619,"score_gpt":0.2822947749776821,"score_spread":0.2375180727218059,"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."}}