{"id":"W4416956238","doi":"10.1145/3769102.3774388","title":"Poster: Leveraging Geo-Spatiality in Geo-Distributed Vector Databases","year":2025,"lang":"","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Embedding; Replication (statistics); k-nearest neighbors algorithm; Routing (electronic design automation); Throughput; Web query classification; Query expansion; Nearest neighbor search","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.001887465,0.0008169491,0.0009207749,0.001147489,0.0006132834,0.001766965,0.001332944,0.0007608515,0.005959837],"category_scores_gemma":[0.004542995,0.0002792631,0.0004698492,0.002021104,0.0005000086,0.003923686,0.001895798,0.001103866,0.004064465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004786489,"about_ca_system_score_gemma":0.0006942711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00417043,"about_ca_topic_score_gemma":0.004921055,"domain_scores_codex":[0.9989279,0.0002976062,0.00008765466,0.0002776416,0.0003188236,0.00009044341],"domain_scores_gemma":[0.9977367,0.0004815641,0.00007909254,0.0009685498,0.000605808,0.0001283469],"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":[0.0008982723,0.0003517607,0.005437448,0.000220606,0.0001856244,0.0001996563,0.0002638207,0.07062481,0.0179052,0.01184691,0.08973454,0.8023313],"study_design_scores_gemma":[0.00009052902,0.0002893679,0.002012021,0.0000280182,0.00006561664,0.000451243,0.0002568118,0.9260511,0.01325098,0.02431122,0.0331329,0.00006018094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.06641909,0.004605306,0.9005847,0.003452942,0.001214397,0.0002565463,0.002086052,0.01082052,0.01056042],"genre_scores_gemma":[0.6432356,0.001991418,0.332355,0.0007390006,0.00105856,0.0001221271,0.00616998,0.000509324,0.01381901],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.005959837,"threshold_uncertainty_score":0.01993763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03578843968987083,"score_gpt":0.2869810144725655,"score_spread":0.2511925747826946,"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."}}