{"id":"W2143085379","doi":"","title":"Efficiently answering top-k typicality queries on large databases","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Discriminative model; Set (abstract data type); Tree (set theory); Measure (data warehouse); Quality (philosophy); Information retrieval; 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":[0.000628092,0.00008957263,0.00007949633,0.00007514103,0.0001093593,0.0001401019,0.0005917261,0.00001380152,0.00008522066],"category_scores_gemma":[0.00003823418,0.00007235783,0.00002778881,0.0002714641,0.00002196118,0.0005895072,0.0005178303,0.00006451917,0.0002078437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001423125,"about_ca_system_score_gemma":0.000007239865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003172156,"about_ca_topic_score_gemma":0.000049605,"domain_scores_codex":[0.9989933,0.00001391448,0.0001392016,0.0003122961,0.0002259715,0.000315325],"domain_scores_gemma":[0.9991846,0.00006838128,0.0000266155,0.0006350927,0.00001863694,0.00006668132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006872338,0.0001327309,0.001559234,0.000007986896,0.000006171613,0.00002701723,0.00005895632,0.000006180657,0.00004429768,0.9434063,0.003594403,0.05114979],"study_design_scores_gemma":[0.0005860783,0.0001355698,0.04494345,0.00003011016,0.000006133835,0.000003120327,0.0002004689,0.01886979,0.01216646,0.0009477593,0.9216454,0.0004656336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01605542,0.00001785789,0.941934,0.0003325492,0.0003871726,0.00007335992,0.00001165864,0.0002554153,0.04093255],"genre_scores_gemma":[0.896396,0.0000117559,0.09761634,0.002419359,0.0001685298,0.000003253295,0.00004969578,0.000008879671,0.003326118],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9424586,"threshold_uncertainty_score":0.2950667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02467601805185922,"score_gpt":0.292098508945551,"score_spread":0.2674224908936918,"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."}}