{"id":"W3122790281","doi":"10.1002/navi.445","title":"Data‐driven protection levels for camera and 3D map‐based safe urban localization","year":2021,"lang":"en","type":"preprint","venue":"NAVIGATION Journal of the Institute of Navigation","topic":"Indoor and Outdoor Localization Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Geological Survey; Canadian Institute for Advanced Research; National Science Foundation","keywords":"GNSS applications; Computer science; Outlier; Position (finance); Weighting; Lidar; Artificial intelligence; Gaussian; Probabilistic logic; Artificial neural network; Data mining; Computer vision; Algorithm; Pattern recognition (psychology); Global Positioning System; Remote sensing; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005630691,0.0002706472,0.0004292565,0.0002032991,0.0001728963,0.0001247835,0.0006114626,0.0004612491,0.000004844333],"category_scores_gemma":[0.0003436348,0.0002358896,0.0001530138,0.0003325715,0.000178626,0.0007146908,0.0002048521,0.0006584349,5.105186e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000246195,"about_ca_system_score_gemma":0.0003277371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002100117,"about_ca_topic_score_gemma":0.00001150409,"domain_scores_codex":[0.9979891,0.0000792287,0.001029708,0.0002579047,0.0004908614,0.0001532037],"domain_scores_gemma":[0.9972076,0.00005310174,0.001081057,0.0006136887,0.0009940383,0.00005045746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003637588,0.00003338628,0.0002459424,0.00158398,0.0001287849,0.000002807021,0.0003220428,0.9802237,0.004598143,0.000217608,0.0005018192,0.01210544],"study_design_scores_gemma":[0.001271911,0.00009426399,0.0005696077,0.004778309,0.0003381615,0.00005145723,0.000183415,0.9061503,0.07703092,0.001834964,0.007311027,0.0003856344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1563638,0.0007286145,0.8377112,0.0004658249,0.003328669,0.0009464484,0.0003457937,0.00009026787,0.00001938932],"genre_scores_gemma":[0.9796939,0.0000660991,0.01877593,0.00003368654,0.0002890835,0.00003075532,0.001056722,0.00004210527,0.00001165829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8233302,"threshold_uncertainty_score":0.9619299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0425697193685205,"score_gpt":0.272000307019412,"score_spread":0.2294305876508915,"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."}}