{"id":"W3069416164","doi":"10.1111/tgis.12680","title":"OpenStreetMap quality assessment using unsupervised machine learning methods","year":2020,"lang":"en","type":"article","venue":"Transactions in GIS","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Volunteered geographic information; Geospatial analysis; Reliability (semiconductor); Computer science; Quality (philosophy); Data science; Feature (linguistics); Quality assurance; Data quality; Data mining; Geography; Engineering; Cartography; Metric (unit)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00198742,0.00009772115,0.0002294258,0.000116433,0.0007931719,0.00006450793,0.0001555248,0.000071016,0.000685197],"category_scores_gemma":[0.0001001997,0.0001021069,0.00009132675,0.0009150667,0.0001333263,0.0003511691,0.000009668624,0.0003059924,0.00001360072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001173044,"about_ca_system_score_gemma":0.0001118887,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.019158,"about_ca_topic_score_gemma":0.004975073,"domain_scores_codex":[0.9979995,0.0008623738,0.0004244593,0.0001597838,0.0003195896,0.0002343153],"domain_scores_gemma":[0.999418,0.0002067354,0.00009647983,0.00009421135,0.00009375821,0.00009078249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00006982293,0.0002474402,0.2225867,0.0003076331,0.0003891686,0.000009031991,0.5599229,0.03951273,0.002829109,0.02135079,0.00005194087,0.1527227],"study_design_scores_gemma":[0.003866132,0.0001811408,0.101119,0.0001599027,0.0001828047,0.00000450114,0.4715374,0.09665708,0.0003900959,0.001080792,0.3233412,0.001479981],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04364891,0.0001426025,0.8993081,0.005949162,0.0003841192,0.0005157378,0.0000147497,0.0002267672,0.04980985],"genre_scores_gemma":[0.9525962,0.00007801041,0.04685654,0.0001768862,0.00003945666,0.00002215493,0.000002692958,0.000007067651,0.0002209705],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9089473,"threshold_uncertainty_score":0.9873735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2001277540490803,"score_gpt":0.4650789032279641,"score_spread":0.2649511491788838,"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."}}