{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000410606,0.000157634,0.0001294401,0.0001841666,0.000207646,0.000685911,0.001269895,0.00003430545,0.0002508045],"category_scores_gemma":[0.00006754787,0.0001361044,0.00004005562,0.0002359376,0.00001833504,0.002605782,0.00101591,0.0001494097,0.0003720288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005360256,"about_ca_system_score_gemma":0.00002706052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001887331,"about_ca_topic_score_gemma":0.0002307799,"domain_scores_codex":[0.9986265,0.0000451716,0.000223394,0.0004313873,0.0002914832,0.0003820866],"domain_scores_gemma":[0.9991654,0.00008549137,0.00007683929,0.0005690024,0.00001815358,0.0000851322],"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":[0.000007551142,0.00006194529,0.0004337162,0.00001166672,0.00002893871,0.00005416447,0.001536729,0.0001998958,0.0003071204,0.05248116,0.1074403,0.8374368],"study_design_scores_gemma":[0.0004236825,0.00004461666,0.0005619141,0.00003555738,0.000007089302,0.00001302528,0.000129868,0.8913096,0.001216308,0.0006654424,0.105248,0.0003449035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002176915,0.00001602672,0.9796424,0.0008612885,0.0005791772,0.0001323563,0.0000364976,0.0003020532,0.01625327],"genre_scores_gemma":[0.4248273,0.000004693256,0.5660424,0.001667562,0.0005283861,0.00001053491,0.0003643918,0.00001436113,0.006540371],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8911098,"threshold_uncertainty_score":0.6614256,"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."}}