{"id":"W4366825774","doi":"10.1080/07350015.2023.2205918","title":"Links and Legibility: Making Sense of Historical U.S. Census Automated Linking Methods","year":2023,"lang":"en","type":"article","venue":"Journal of Business and Economic Statistics","topic":"Census and Population Estimation","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Legibility; Census; Handwriting; Statistics; Computer science; Econometrics; Geography; Artificial intelligence; Mathematics; Demography; Advertising; Sociology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02379818,0.0004835977,0.0004011017,0.006566227,0.001253936,0.005183736,0.001101587,0.001104747,0.002784826],"category_scores_gemma":[0.3123404,0.0007156204,0.0005136442,0.008227806,0.003136341,0.00985628,0.00351262,0.001530968,0.0004805626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001800644,"about_ca_system_score_gemma":0.0008833261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009893896,"about_ca_topic_score_gemma":0.01201768,"domain_scores_codex":[0.9833435,0.01134138,0.0008550702,0.002052526,0.00213828,0.0002691822],"domain_scores_gemma":[0.7841588,0.1590479,0.02173468,0.02289973,0.01091625,0.001242579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003504709,0.0001126855,0.6763362,0.0003070621,0.0004848826,0.000220712,0.008017967,0.05820605,0.0006111105,0.05040769,0.005109395,0.1998357],"study_design_scores_gemma":[0.00006524321,0.0002316692,0.5057743,0.0007562893,0.0002664229,0.0004388297,0.00365827,0.2728971,0.003792995,0.1829395,0.02896067,0.0002187331],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7864409,0.004144319,0.17915,0.004652971,0.0002650638,0.0001284996,0.003150693,0.0007176995,0.02134994],"genre_scores_gemma":[0.9681476,0.0005288565,0.02910996,0.0001819787,0.0001217504,0.0000512898,0.0008504558,0.0001675708,0.000840516],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02379818,"threshold_uncertainty_score":0.1258583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1118148885207922,"score_gpt":0.3985771132833354,"score_spread":0.2867622247625433,"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."}}