{"id":"W2133246278","doi":"10.14778/1453856.1453895","title":"Efficient search for the top-k probable nearest neighbors in uncertain databases","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining; Query optimization; Online aggregation; k-nearest neighbors algorithm; Query language; Semantics (computer science); Information retrieval; Sargable; Object (grammar); Point (geometry); Database; Feature (linguistics); Web query classification; Web search query; Search engine; Artificial intelligence","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":[0.0006452869,0.0001281898,0.0001361242,0.00008646279,0.000266293,0.00009554292,0.001869526,0.00001552029,0.000005675796],"category_scores_gemma":[0.00006846619,0.00007130609,0.00006995328,0.0006123806,0.0001055648,0.0002618988,0.001130636,0.0001058427,0.000005242524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006247049,"about_ca_system_score_gemma":0.00004495695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001971336,"about_ca_topic_score_gemma":0.000007067521,"domain_scores_codex":[0.9985974,0.000007216346,0.0002319851,0.0003326134,0.0004692359,0.0003615712],"domain_scores_gemma":[0.9993073,0.0001152242,0.0001000381,0.0003355957,0.0001031643,0.00003867878],"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":[0.0001579421,0.001646169,0.07907028,0.0006771564,0.0001951438,0.000008744637,0.006120609,0.02463807,0.003978821,0.796243,0.04499962,0.04226441],"study_design_scores_gemma":[0.004220396,0.0003902789,0.04706459,0.0004220211,0.00006859218,0.00002580775,0.001528066,0.7831204,0.0797512,0.002918605,0.07962988,0.0008601595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8509537,0.00151265,0.08600765,0.03346977,0.002081388,0.0124648,0.0001696182,0.0003754961,0.01296495],"genre_scores_gemma":[0.9737758,0.00007928286,0.02437377,0.0003293639,0.00009826134,0.0002922222,0.000005310293,0.00001474321,0.001031264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7933244,"threshold_uncertainty_score":0.3474076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05346318793657699,"score_gpt":0.2715280562480217,"score_spread":0.2180648683114447,"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."}}