{"id":"W2007993174","doi":"10.1145/1317331.1317335","title":"A comparison of five probabilistic view-size estimation techniques in OLAP","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Université du Québec à Montréal","keywords":"Online analytical processing; Computer science; Probabilistic logic; Estimation; Data mining; Artificial intelligence; Data warehouse; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0008825439,0.000107555,0.0002319754,0.0001762706,0.00001985006,0.00003603138,0.0007540108,0.00006841743,0.000010133],"category_scores_gemma":[0.0004159461,0.0000975072,0.00002674569,0.0005185072,0.00005779694,0.0003931023,0.0002537332,0.0001079983,0.000006544256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006980392,"about_ca_system_score_gemma":0.00003779812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002301793,"about_ca_topic_score_gemma":0.0001746371,"domain_scores_codex":[0.9988104,0.00003664105,0.0004733035,0.0002687216,0.0002134531,0.0001974562],"domain_scores_gemma":[0.9988011,0.0003637386,0.0001510968,0.0005697013,0.00007660449,0.00003776557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002571413,0.0007714491,0.0160895,0.0001561217,0.000009703206,0.00001664417,0.003038816,0.00006334679,0.004623464,0.1637437,0.007029761,0.8044318],"study_design_scores_gemma":[0.0003631528,0.0007296552,0.04055379,0.0004885665,0.00001052654,0.00001979419,0.0001490706,0.2600918,0.6222869,0.07294437,0.001786344,0.0005759828],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0243424,0.00002077822,0.9655767,0.0001344363,0.0000316974,0.0003711814,0.000002107814,0.0006297524,0.008890936],"genre_scores_gemma":[0.5065423,8.886237e-7,0.4933769,0.00002821039,0.000003600811,0.00001271679,0.000002587001,0.00000303666,0.00002984057],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8038558,"threshold_uncertainty_score":0.3976228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02678005254023122,"score_gpt":0.3486871844326072,"score_spread":0.321907131892376,"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."}}