{"id":"W2949197339","doi":"10.48550/arxiv.cs/0703058","title":"A Comparison of Five Probabilistic View-Size Estimation Techniques in OLAP","year":2007,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Probabilistic logic; Computer science; Reliability (semiconductor); Online analytical processing; Estimation; Hash function; Algorithm; Data mining; Statistics; Mathematics; Artificial intelligence; Data warehouse","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":[0.001130725,0.0003807237,0.0007792692,0.0004033429,0.00004095336,0.00008471827,0.002388669,0.000422318,0.000009553062],"category_scores_gemma":[0.0009852062,0.0003930327,0.0001124638,0.0005421549,0.0001552011,0.0003410678,0.002575131,0.0008279625,0.00002171047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002501998,"about_ca_system_score_gemma":0.0002123931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005425508,"about_ca_topic_score_gemma":0.0001081121,"domain_scores_codex":[0.997102,0.000152325,0.001048103,0.0009031149,0.0004215282,0.0003729564],"domain_scores_gemma":[0.9965584,0.0004645411,0.0007439923,0.001948348,0.0002094207,0.00007532327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006993549,0.00196067,0.7016717,0.002439364,0.000104762,0.00009994804,0.008023119,0.001169798,0.002311473,0.01036043,0.00807825,0.2637106],"study_design_scores_gemma":[0.0006459801,0.0008546741,0.5115526,0.0073098,0.0001099966,0.00002963451,0.0001154947,0.1944456,0.2044578,0.07571708,0.002401859,0.002359518],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5009536,0.0002301112,0.4937886,0.000277832,0.0002698141,0.001390061,0.00003524578,0.001245477,0.001809355],"genre_scores_gemma":[0.6282617,0.00001874853,0.3714101,0.00004838778,0.00002645292,0.000140322,0.00004802509,0.00001775077,0.00002847923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.261351,"threshold_uncertainty_score":0.9998522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0650200978567504,"score_gpt":0.3657233901605293,"score_spread":0.300703292303779,"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."}}