{"id":"W2588190562","doi":"10.3141/2647-05","title":"Identifying the Bias: Evaluating Effectiveness of Automatic Data Collection Methods in Estimating Details of Bus Dwell Time","year":2017,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Dwell time; Data collection; Computer science; Statistics; Mathematics; Psychology","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":[0.0247797,0.0001933703,0.0005519988,0.0007177821,0.0006189751,0.0001337598,0.001983858,0.0001314622,0.00005096657],"category_scores_gemma":[0.001774784,0.0001340445,0.0001944765,0.00104288,0.0004766474,0.000905842,0.00002489796,0.001545725,0.000002232066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002014811,"about_ca_system_score_gemma":0.0003556415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004109205,"about_ca_topic_score_gemma":0.003441566,"domain_scores_codex":[0.9931666,0.002391477,0.001536331,0.0002655592,0.002081029,0.0005589499],"domain_scores_gemma":[0.9930137,0.003303459,0.0007546709,0.00101777,0.001813541,0.0000968043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001275956,0.0001696698,0.2922997,0.006516334,0.0006168986,0.00006444181,0.009202851,0.1891691,0.3713529,0.0003271205,0.0004162355,0.1285888],"study_design_scores_gemma":[0.001058987,0.0001925713,0.826858,0.002643821,0.00006881666,8.29858e-7,0.0009858989,0.1290549,0.03660279,0.002381278,0.00003197551,0.0001200759],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9661182,0.0002219512,0.03175209,0.00009339034,0.0008051991,0.0008864916,0.00002406473,0.00001774128,0.00008090326],"genre_scores_gemma":[0.944612,0.000183422,0.05498184,0.000001221939,0.0001015184,0.00003704137,0.000009157834,0.00004262468,0.00003116241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5345583,"threshold_uncertainty_score":0.85882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2240752638579003,"score_gpt":0.4941593719351079,"score_spread":0.2700841080772076,"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."}}