{"id":"W2013530697","doi":"10.1016/j.aap.2006.09.009","title":"Empirical Bayes before–after safety studies: Lessons learned from two decades of experience and future directions","year":2006,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":266,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Sophistication; Crash; Bayes' theorem; Ranking (information retrieval); Empirical research; Risk analysis (engineering); Computer science; Regression toward the mean; Engineering; Transport engineering; Data science; Operations research; Statistics; Bayesian probability; Machine learning; Mathematics; Artificial intelligence; Business","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":[0.0001036313,0.0001458427,0.0003033132,0.0001993657,0.00009070767,0.00003136215,0.00007981846,0.00006464204,0.00008091382],"category_scores_gemma":[0.00001469273,0.0001282556,0.0002015793,0.0005208252,0.00003957898,0.0002400572,0.00004410172,0.0001041199,0.000001708431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007278588,"about_ca_system_score_gemma":0.000005339748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000223302,"about_ca_topic_score_gemma":0.004984645,"domain_scores_codex":[0.9990574,0.00003753612,0.0003496606,0.0002286805,0.0001595574,0.0001671296],"domain_scores_gemma":[0.9995958,0.00003447091,0.00007601969,0.0001950845,0.00006787328,0.00003076795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002113526,0.00001675464,0.9426725,0.000005780299,0.001084276,0.000003009456,0.00298482,0.004754707,0.0009432547,0.00009535412,0.00007994456,0.04733849],"study_design_scores_gemma":[0.0002389125,0.00001515378,0.9856834,0.00004550221,0.0009605416,9.023039e-7,0.001647527,0.001335472,0.00287026,0.003928337,0.003113718,0.0001603129],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988179,0.003824714,0.007339335,0.0001517518,0.0002650662,0.00007244742,0.000001803837,0.0000747115,0.00009117606],"genre_scores_gemma":[0.9961216,0.001722612,0.001417037,0.000005997646,0.0005530787,0.00003002324,0.00003406855,0.00001249194,0.0001031213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04717818,"threshold_uncertainty_score":0.5230113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02028807076043185,"score_gpt":0.336758892368909,"score_spread":0.3164708216084772,"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."}}