{"id":"W2139943667","doi":"10.3141/2338-08","title":"Evaluating the Performance of Algorithms for the Detection of Travel Time Outliers","year":2013,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Algorithm; Bluetooth; Outlier; Computer science; Anomaly detection; Identification (biology); Data mining; Detector; Range (aeronautics); Real-time computing; Engineering; Artificial intelligence; Wireless","routes":{"ca_aff":true,"ca_fund":false,"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":[0.004936661,0.0001503291,0.0002746251,0.0004443506,0.000381948,0.0000479367,0.0008637608,0.00009968095,0.00008417352],"category_scores_gemma":[0.0001014797,0.00008620846,0.0002908295,0.001020951,0.0004616481,0.0004022061,0.000004483437,0.0009619053,0.000005698274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009049259,"about_ca_system_score_gemma":0.0001190985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001159151,"about_ca_topic_score_gemma":0.0009987061,"domain_scores_codex":[0.9960374,0.0003419692,0.001072574,0.0001549825,0.00196767,0.0004254383],"domain_scores_gemma":[0.9959901,0.001128516,0.0002950736,0.000361097,0.002132533,0.00009268701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001541792,0.0002890074,0.01042608,0.00174492,0.001011354,0.000002869886,0.007803957,0.1039452,0.335475,0.0009730751,0.01574571,0.521041],"study_design_scores_gemma":[0.001389194,0.00166345,0.6614882,0.0003157165,0.0001370384,4.34902e-7,0.002804612,0.2754159,0.05401609,0.0004714637,0.002135012,0.0001629903],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9531561,0.000235763,0.04299367,0.0009509447,0.0003617307,0.002101893,0.00003437851,0.00007749794,0.00008802194],"genre_scores_gemma":[0.9965628,0.001081036,0.001723085,0.0000116912,0.00008640021,0.0002593316,0.000004855137,0.00003650785,0.0002343139],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6510621,"threshold_uncertainty_score":0.4179053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08891188676715688,"score_gpt":0.3747945485001709,"score_spread":0.285882661733014,"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."}}