{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001810466,0.0003610862,0.0004028543,0.0002907549,0.00007622432,0.0002050256,0.001623297,0.0002381995,0.000009897413],"category_scores_gemma":[0.00001110433,0.0003696877,0.00005553706,0.0003208809,0.00002326059,0.0004474787,0.0002824909,0.0009718183,0.00005668348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005276077,"about_ca_system_score_gemma":0.000114789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004678774,"about_ca_topic_score_gemma":0.00003647497,"domain_scores_codex":[0.9980478,0.00003339448,0.0003162533,0.001129434,0.00016593,0.0003071297],"domain_scores_gemma":[0.9977525,0.000137357,0.00005294507,0.001834882,0.00003041713,0.0001918237],"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":[0.00007455658,0.001271718,0.00005376732,0.002733442,0.000342583,0.0006693196,0.004159573,0.2115306,0.006107995,0.00371217,0.01439734,0.754947],"study_design_scores_gemma":[0.0003537255,0.00004098092,0.0001306349,0.0004062023,0.00002223862,0.00002169665,0.00000792215,0.9866337,0.001402971,0.0001311331,0.01039579,0.0004529745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009919672,0.001389115,0.9944337,0.0003046493,0.001739935,0.0002254712,0.0004350209,0.0002703157,0.0002097966],"genre_scores_gemma":[0.8869796,0.001430771,0.1105817,0.00008390812,0.0003419995,0.00008061206,0.0002495703,0.00007001224,0.0001817529],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8859877,"threshold_uncertainty_score":0.9998755,"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."}}