{"id":"W2164509564","doi":"10.1145/1097064.1097078","title":"Finding corresponding objects when integrating several geo-spatial datasets","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Join (topology); Computer science; Data mining; k-nearest neighbors algorithm; Precision and recall; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009978901,0.001277296,0.001934927,0.01042864,0.001503274,0.004938866,0.003141959,0.002762886,0.001017053],"category_scores_gemma":[0.03413608,0.001209363,0.00204519,0.01109689,0.001042517,0.007266059,0.005026308,0.001319267,0.0008368216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008876865,"about_ca_system_score_gemma":0.001335326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002853866,"about_ca_topic_score_gemma":0.004228113,"domain_scores_codex":[0.988261,0.002208191,0.00122539,0.002228473,0.005597648,0.0004793156],"domain_scores_gemma":[0.9849243,0.007141155,0.00189991,0.003480942,0.002129002,0.0004246029],"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":[0.001074936,0.0008419748,0.06901994,0.001156944,0.001052433,0.003051774,0.003629381,0.1266783,0.03760704,0.0212971,0.006759585,0.7278306],"study_design_scores_gemma":[0.0001325093,0.0004638008,0.03185152,0.0003256851,0.0009420763,0.003229542,0.004748248,0.7373582,0.1026455,0.07260794,0.04540759,0.000287447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09147626,0.0007622645,0.9016306,0.0002781477,0.00007954342,0.0005826921,0.001234279,0.002255191,0.001700909],"genre_scores_gemma":[0.1489407,0.0002840497,0.8456572,0.00006665193,0.00004881264,0.0002703866,0.004096223,0.0001040027,0.0005319672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01042864,"threshold_uncertainty_score":0.05277413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01813873062087971,"score_gpt":0.2586099181512564,"score_spread":0.2404711875303767,"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."}}