{"id":"W3008560015","doi":"10.1109/icmla.2019.00197","title":"Ranking Clusters of Postal Codes to Improve Recruitment in the Canadian Armed Forces","year":2019,"lang":"en","type":"article","venue":"","topic":"Census and Population Estimation","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Department of National Defence","funders":"","keywords":"Ranking (information retrieval); Rank (graph theory); Set (abstract data type); Unsupervised learning; Computer science; Population; Military personnel; Machine learning; Training set; Artificial intelligence; Operations research; Engineering; Mathematics; Political science; Medicine; Law; Combinatorics","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":[0.000345033,0.00004702103,0.0000852712,0.00007612395,0.00002824826,0.00001495534,0.00006922174,0.00002644556,0.0001050963],"category_scores_gemma":[0.00005814281,0.00003108246,0.0000215664,0.00008391098,0.000006109179,0.00003842398,0.000008791149,0.00003378039,0.00001177653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007266683,"about_ca_system_score_gemma":0.00003921325,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05340789,"about_ca_topic_score_gemma":0.5277286,"domain_scores_codex":[0.9995109,0.0000280484,0.0001678706,0.00006770818,0.000118308,0.0001071647],"domain_scores_gemma":[0.9996271,0.0001343594,0.00004690676,0.0001322311,0.00002879498,0.00003059688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001747772,0.0001932608,0.1732471,0.0005472979,0.00007011853,0.000005703278,0.06674831,0.003364492,0.004682368,0.704872,0.005757262,0.04033726],"study_design_scores_gemma":[0.007468993,0.001285795,0.5376527,0.0008070952,0.0001628078,0.00002934276,0.02069323,0.1764769,0.01215075,0.2196554,0.02202369,0.00159337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.983633,0.00000264599,0.0004182338,0.001409331,0.00008725016,0.0009936419,0.00000832363,0.000006931982,0.01344062],"genre_scores_gemma":[0.9959189,3.395194e-7,0.003331399,0.0003658805,0.000009633216,0.00001718618,0.000008335174,0.000004537946,0.0003437935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4852166,"threshold_uncertainty_score":0.9528955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08154883476620853,"score_gpt":0.3465379927603617,"score_spread":0.2649891579941531,"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."}}