{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001063981,0.00009464977,0.00006553702,0.00006663921,0.0005025943,0.0006620637,0.001397598,0.00001756113,0.0000468939],"category_scores_gemma":[0.00002007843,0.00004613274,0.000071976,0.0002333728,0.00004987862,0.0003837403,0.0001313335,0.0002386325,0.0000995493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005102058,"about_ca_system_score_gemma":0.00002746277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001985962,"about_ca_topic_score_gemma":0.000006544608,"domain_scores_codex":[0.9989637,0.0001252873,0.0001691236,0.0001325776,0.0003823318,0.0002269986],"domain_scores_gemma":[0.9992129,0.00007748162,0.0001216164,0.0005186553,0.00003463183,0.00003473166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005336108,0.0006412743,0.001296106,0.00001264557,0.00006431521,0.0001282153,0.0004837118,0.005667223,0.001282399,0.375942,0.3447168,0.269712],"study_design_scores_gemma":[0.0005922371,0.0001784756,0.008094938,0.00003803339,0.00002212098,0.00005483617,0.00004914692,0.5234728,0.0003471537,0.01831453,0.4486172,0.0002184574],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03660053,0.000124384,0.9196177,0.02518944,0.001553098,0.0002327394,0.000002655818,0.0001180891,0.01656142],"genre_scores_gemma":[0.9831461,0.00001583918,0.01003765,0.002071194,0.000751622,0.000008051918,0.00000420153,0.00001137747,0.003953944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9465456,"threshold_uncertainty_score":0.6384296,"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."}}