{"id":"W4308885220","doi":"10.1061/jtepbs.teeng-6985","title":"An Approach for Detecting Data Anomalies at Permanent Cycling Count Stations","year":2022,"lang":"en","type":"article","venue":"Journal of Transportation Engineering Part A Systems","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Flagging; Outlier; Count data; Computer science; Data set; Data mining; Anomaly detection; Set (abstract data type); Cycling; Statistics; Geography; Artificial intelligence; Mathematics; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006127228,0.0001197989,0.0001935651,0.0002156534,0.0001448458,0.00004086949,0.0002759723,0.00002811293,0.000004513676],"category_scores_gemma":[0.000006620195,0.0001328158,0.00006017315,0.0001301465,0.000005295185,0.0003622037,0.000007128054,0.0001579253,2.011691e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000153812,"about_ca_system_score_gemma":0.00001415888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000430103,"about_ca_topic_score_gemma":0.000004398655,"domain_scores_codex":[0.9988416,0.00001778924,0.0005748879,0.0001250949,0.0002866945,0.0001539566],"domain_scores_gemma":[0.9994699,0.00003587485,0.0001499561,0.0002174754,0.0000576788,0.00006913222],"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":[0.0000132669,0.00002944364,0.0002081369,0.0002650408,0.00008649567,0.000004473233,0.000637935,0.9935154,0.002434678,0.0001888839,0.002424318,0.0001919318],"study_design_scores_gemma":[0.0003393939,0.00007806001,0.0008012337,0.00002969047,0.00007642568,0.00003364777,0.0009735044,0.9496144,0.0001514812,7.023848e-7,0.04776114,0.0001403337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1073603,0.0004315088,0.8893967,0.000009797895,0.001228816,0.0003257276,0.0004066986,0.0008002989,0.00004025916],"genre_scores_gemma":[0.9901069,0.00004027563,0.008943029,0.00000592885,0.0001841223,0.0001079229,0.0005557992,0.00004038237,0.0000156393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8827466,"threshold_uncertainty_score":0.541607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02696523991095251,"score_gpt":0.2409727155396921,"score_spread":0.2140074756287396,"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."}}