{"id":"W2024336226","doi":"10.1007/s00778-006-0015-0","title":"Histograms based on the minimum description length principle","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Histogram; Computer science; Data mining; Set (abstract data type); Representation (politics); Overhead (engineering); Online analytical processing; Data set; Algorithm; Pattern recognition (psychology); Artificial intelligence; Image (mathematics); Data warehouse","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001388685,0.0004242211,0.001290412,0.002103799,0.0006321134,0.001905788,0.001771838,0.001031972,0.006366499],"category_scores_gemma":[0.00702326,0.0005906429,0.0006776342,0.00223657,0.001008997,0.004397087,0.001938121,0.001750517,0.001464011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007442914,"about_ca_system_score_gemma":0.0008641944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001694131,"about_ca_topic_score_gemma":0.001252762,"domain_scores_codex":[0.9989535,0.0002712279,0.00005018016,0.0001949072,0.0004239116,0.0001063305],"domain_scores_gemma":[0.9958961,0.002351341,0.0002426839,0.0006529803,0.000651457,0.000205485],"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":[0.0007357134,0.0001316061,0.00219497,0.0003819184,0.0001160994,0.0001668061,0.0001613401,0.1294976,0.01586854,0.3271496,0.01295596,0.5106398],"study_design_scores_gemma":[0.00005403048,0.00009874269,0.001088511,0.00003181296,0.00003216869,0.0001517462,0.00004149525,0.7658569,0.004949989,0.2213033,0.006330318,0.000061004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008013211,0.0005881589,0.9888158,0.0002570182,0.00006814592,0.00002733497,0.0002401323,0.0005421258,0.001448094],"genre_scores_gemma":[0.4229415,0.001945704,0.5633664,0.0005369673,0.0006358157,0.0002171757,0.002124734,0.0007606627,0.007471071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006366499,"threshold_uncertainty_score":0.02129805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0234515832102263,"score_gpt":0.2229272232546076,"score_spread":0.1994756400443813,"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."}}