{"id":"W2788558106","doi":"10.1145/3178876.3186078","title":"Strategies for Geographical Scoping and Improving a Gazetteer","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scope (computer science); Hierarchy; Computer science; Boundary (topology); Baseline (sea); Information retrieval; Probabilistic logic; Quality (philosophy); Pairwise comparison; Volunteered geographic information; Data mining; Geography; Position (finance); Geotagging; Data science; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01042648,0.002178991,0.002610921,0.0100683,0.003137722,0.003993725,0.004833778,0.002586847,0.004664691],"category_scores_gemma":[0.0519868,0.001368274,0.001567467,0.00652692,0.002224772,0.0103713,0.01012705,0.002396896,0.002479106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001905612,"about_ca_system_score_gemma":0.003332807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01524811,"about_ca_topic_score_gemma":0.02023605,"domain_scores_codex":[0.9926932,0.002451823,0.0005772923,0.00187072,0.002017467,0.0003895396],"domain_scores_gemma":[0.9739425,0.009589489,0.002168747,0.008186297,0.005445978,0.0006669956],"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":[0.0004562783,0.0002857065,0.02028915,0.0009945014,0.000180494,0.0005466848,0.009529402,0.05159984,0.02602851,0.0415712,0.02103554,0.8274826],"study_design_scores_gemma":[0.0002155299,0.0004459885,0.01540779,0.0007940091,0.0004083669,0.001312943,0.008196685,0.7342793,0.04731635,0.1019563,0.08921008,0.0004566345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03257488,0.001379867,0.9533122,0.001009757,0.00008775557,0.0004107664,0.0005510009,0.006102303,0.004571503],"genre_scores_gemma":[0.2592115,0.0008204624,0.7323604,0.0002948569,0.00008626819,0.0004798502,0.002011537,0.001269133,0.003465968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01524811,"threshold_uncertainty_score":0.05514115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01891839314741942,"score_gpt":0.2677750830947065,"score_spread":0.2488566899472871,"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."}}