{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009338247,0.00009084636,0.0003732321,0.0001656197,0.00006115177,0.00002846775,0.00003248567,0.00009648604,0.000009209351],"category_scores_gemma":[0.0005813437,0.00008265418,0.00002738976,0.0001027876,0.00003478262,0.00008816176,0.00003504732,0.0001336657,7.066458e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001259624,"about_ca_system_score_gemma":0.00005027445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003320052,"about_ca_topic_score_gemma":0.00001254585,"domain_scores_codex":[0.9989605,0.00005855235,0.000712769,0.00009133073,0.00007179895,0.0001050528],"domain_scores_gemma":[0.9981273,0.000838238,0.0007085931,0.00008557642,0.0001945919,0.00004569623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005066067,0.0002977301,0.1305328,0.006078108,0.0005962874,0.000315567,0.005924465,0.01841015,0.001472713,0.2168964,0.03813285,0.5808362],"study_design_scores_gemma":[0.0008281123,0.00005779048,0.2527305,0.0002625919,0.0001765336,0.0003003883,0.00009483794,0.6368859,0.00002217548,0.1048313,0.003607409,0.0002023145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7857171,0.0002075637,0.2123832,0.0004133732,0.0009684035,0.00008425758,0.0000917449,0.00005030806,0.00008403832],"genre_scores_gemma":[0.633494,0.00024685,0.3660176,0.00001753505,0.00015766,4.858579e-7,0.00001097571,0.00001858153,0.00003621756],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6184758,"threshold_uncertainty_score":0.337054,"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."}}