{"id":"W4409641820","doi":"10.1109/tim.2025.3562977","title":"Deep-Learning-Enhanced Outlier Detection for Precise GNSS Positioning With Smartphones","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"GNSS positioning and interference","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"GNSS applications; Computer science; Global Positioning System; Artificial intelligence; Anomaly detection; Deep learning; Outlier; Remote sensing; Computer vision; Real-time computing; Telecommunications; Geology","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":[0.0001055398,0.0001355458,0.0001034074,0.0001553766,0.0003071488,0.00007573893,0.00003377304,0.00004939959,0.00001591733],"category_scores_gemma":[0.000002905476,0.0001330237,0.00003692329,0.0001362615,0.00002508102,0.0001512309,3.190379e-7,0.0001322242,0.000004998843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001788679,"about_ca_system_score_gemma":0.00001540956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009024015,"about_ca_topic_score_gemma":0.0001310972,"domain_scores_codex":[0.999317,0.00002419953,0.0001737935,0.0001745637,0.0001692121,0.0001412427],"domain_scores_gemma":[0.9996985,0.00002150334,0.00002751097,0.00007563442,0.0001329873,0.00004383358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004932095,0.0001578624,0.00005307997,0.0002790556,0.0003189123,2.293088e-7,0.001518136,0.2821157,0.2188555,0.0001077018,0.00004592638,0.4960547],"study_design_scores_gemma":[0.001676177,0.0004297358,0.000943154,0.0003670816,0.0001126283,0.00000361098,0.0006136519,0.04430103,0.9509793,0.0000705808,0.0003003037,0.0002027789],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1016939,0.00004203878,0.8955448,0.00004938054,0.0005634215,0.0003356113,0.000003371618,0.0001910485,0.001576417],"genre_scores_gemma":[0.9980835,0.00006208884,0.001175194,0.00004970033,0.00001300414,0.0003947021,0.000004623352,0.0000156746,0.0002015366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8963895,"threshold_uncertainty_score":0.5424547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01130169649567451,"score_gpt":0.217600366630156,"score_spread":0.2062986701344815,"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."}}