{"id":"W2157044362","doi":"10.1007/s00778-008-0128-8","title":"Top-k typicality queries and efficient query answering methods on large databases","year":2009,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Discriminative model; Set (abstract data type); Tree (set theory); Information retrieval; Measure (data warehouse); Quality (philosophy); Series (stratigraphy); Data mining; Artificial intelligence; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.001832644,0.00009570341,0.0001087534,0.00006448283,0.0003647125,0.0003854737,0.0006034255,0.00001287563,0.00001774358],"category_scores_gemma":[0.00007951713,0.00005752336,0.00003563786,0.0001683781,0.00003708775,0.0003801336,0.0002740014,0.0002211391,0.000009791759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001467214,"about_ca_system_score_gemma":0.00001538099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004490804,"about_ca_topic_score_gemma":0.000001218719,"domain_scores_codex":[0.9990261,0.0001957441,0.0001602868,0.0001744508,0.0002028323,0.0002405884],"domain_scores_gemma":[0.9992967,0.0001120334,0.00007292708,0.0004200904,0.00002229746,0.00007598586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002775167,0.0001656695,0.000320996,0.000007510646,0.00002873058,0.0000553829,0.0006347288,0.0002013123,0.0004404977,0.3266939,0.002776769,0.6686468],"study_design_scores_gemma":[0.002295894,0.0009368299,0.1412608,0.0003115593,0.00009617844,0.0007130667,0.0009392739,0.2394011,0.009359151,0.05078971,0.5527018,0.001194638],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03587357,0.0003670431,0.9573062,0.004453131,0.0003983241,0.00006200497,0.000006049914,0.00005373045,0.001479963],"genre_scores_gemma":[0.6142283,0.0004513696,0.3793693,0.00477437,0.0007101229,0.000002718042,0.000005661943,0.00001195537,0.0004461829],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6674522,"threshold_uncertainty_score":0.3717132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03418460099070763,"score_gpt":0.3495786809841878,"score_spread":0.3153940799934802,"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."}}