{"id":"W2950155282","doi":"10.48550/arxiv.1012.4889","title":"Tight Bounds for Lp Samplers, Finding Duplicates in Streams, and Related Problems","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Combinatorics; Upper and lower bounds; Mathematics; Space (punctuation); Binary logarithm; Alphabet; Discrete mathematics; Mathematical analysis; Computer science","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":[0.01644223,0.004388293,0.005435191,0.004057551,0.004614344,0.008775155,0.01018492,0.00541495,0.0120079],"category_scores_gemma":[0.110824,0.002869476,0.003758699,0.007202999,0.007327057,0.03340418,0.01091486,0.01290052,0.003585176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006631915,"about_ca_system_score_gemma":0.00602123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003939714,"about_ca_topic_score_gemma":0.003169802,"domain_scores_codex":[0.9787287,0.006615717,0.001479262,0.004320744,0.006019045,0.002836506],"domain_scores_gemma":[0.8736592,0.1025316,0.004088391,0.0123228,0.005280763,0.00211737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00182012,0.0007591384,0.004098849,0.00190954,0.0004177369,0.0005770635,0.001671073,0.2770716,0.005946208,0.5012542,0.02321432,0.1812602],"study_design_scores_gemma":[0.0001702173,0.0002241745,0.0003172566,0.0001702992,0.0001477595,0.0003709638,0.0002402943,0.4263308,0.004103718,0.5601397,0.007710159,0.00007456454],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01953442,0.006457062,0.9565901,0.004099042,0.000359079,0.0002723818,0.0006242145,0.002668613,0.009395055],"genre_scores_gemma":[0.3484579,0.007177349,0.6163076,0.00371915,0.002691448,0.001672827,0.002160396,0.002554805,0.01525852],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01644223,"threshold_uncertainty_score":0.08695585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08367135343070269,"score_gpt":0.216206792013486,"score_spread":0.1325354385827833,"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."}}