{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001496129,0.00005270311,0.00005208782,0.00005599641,0.0001047836,0.0005801282,0.0002733736,0.00001553278,0.00001036],"category_scores_gemma":[0.000006470458,0.00004229352,0.00001576032,0.0001096712,0.00005552438,0.0009660122,0.0002550391,0.00002144349,0.000005618389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001617414,"about_ca_system_score_gemma":0.00001363998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001971822,"about_ca_topic_score_gemma":0.00002277905,"domain_scores_codex":[0.9994897,0.000004843756,0.00006915336,0.000214366,0.00006712044,0.0001548812],"domain_scores_gemma":[0.999716,0.00002501085,0.00001653854,0.00018316,0.00002917979,0.0000300587],"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":[0.000002052325,0.00001196788,0.0001523254,0.00006189547,0.00001042824,0.000001108498,0.000110886,2.842312e-7,0.0003643463,0.7934873,0.002364498,0.2034329],"study_design_scores_gemma":[0.001333109,0.0007248266,0.003700715,0.0001771244,0.0000211735,0.000008582743,0.0005276804,0.8897361,0.001514783,0.08627488,0.01530717,0.0006739102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002805721,0.00002826368,0.99093,0.0006284343,0.0001348644,0.0001500185,7.504481e-7,0.0001091632,0.005212838],"genre_scores_gemma":[0.4592171,0.000008164858,0.5389865,0.0010502,0.0002849367,0.00002786582,0.000002769678,0.000006240394,0.0004162619],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8897358,"threshold_uncertainty_score":0.5594189,"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."}}