{"id":"W2621444302","doi":"10.21433/b3114hp830d6","title":"Outlier Detection in OpenStreetMap Data using the Random Forest Algorithm","year":2016,"lang":"en","type":"article","venue":"International Conference on GIScience Short Paper Proceedings","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Random forest; Outlier; Computer science; Anomaly detection; Algorithm; Data mining; Artificial intelligence","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":[0.002458259,0.0001500149,0.0001562711,0.00024902,0.0006747976,0.0004243923,0.00174649,0.0000766154,0.0001897001],"category_scores_gemma":[0.0006204105,0.00008784083,0.00004290446,0.0005184261,0.0007943364,0.002692194,0.0003453651,0.0001456796,0.00005107269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001867643,"about_ca_system_score_gemma":0.0001439651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001172401,"about_ca_topic_score_gemma":0.004166069,"domain_scores_codex":[0.9975617,0.0000314205,0.0004105309,0.0004247344,0.0011942,0.0003774491],"domain_scores_gemma":[0.9987668,0.0001106855,0.0001538566,0.0002122012,0.000681846,0.00007461016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001799155,0.0001612885,0.2055288,0.00001516877,0.0001138513,0.000008228594,0.03205447,0.00002721728,0.01407201,0.3434847,0.001086342,0.4032681],"study_design_scores_gemma":[0.006891227,0.0004162727,0.2113739,0.002263785,0.00009946802,0.0001058781,0.2466818,0.1271133,0.002708519,0.0481563,0.3511763,0.003013253],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3844557,0.00003714925,0.03065532,0.0256489,0.004120964,0.002190399,0.00009416362,0.0002111617,0.5525863],"genre_scores_gemma":[0.997889,0.00009524116,0.000386154,0.0002493899,0.0002361522,0.00005460777,0.000002232057,0.000006005381,0.001081199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6134334,"threshold_uncertainty_score":0.5190066,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1129588050489322,"score_gpt":0.3611996327628706,"score_spread":0.2482408277139385,"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."}}