{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T07:19:20Z","timestamp":1793949560811,"version":"4.8.0"},"reference-count":48,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"6824","content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Science"],"published-print":{"date-parts":[[2026,11,5]]},"abstract":"<jats:p>The 2020 United States Census adopted differential privacy to protect individual confidentiality, adding calibrated noise to summary demographic measurements that are then reconciled into population tables. We developed BlueDown, a postprocessing algorithm that combines techniques from linear regression and constrained optimization while exploiting measurement structure for efficiency. On 2020 Census data, BlueDown reduced the error of groupings by race at the county level by 21 to 36% and of all county-level groupings by 9 to 58%; at the tract level, it reduced error of groupings by housing type by 38 to 61%. These gains came at no cost to confidentiality or computational efficiency and would improve the validity of research relying on this definitive dataset and analyses used to guide the distribution of more than $1.5 trillion in annual federal spending.<\/jats:p>","DOI":"10.1126\/science.aej1765","type":"journal-article","created":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T19:02:22Z","timestamp":1793905342000},"page":"686-692","update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":1,"title":["Denoising the US Census: Succinct block hierarchical regression"],"prefix":"10.1126","volume":"394","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1555-5321","authenticated-orcid":true,"given":"Badih","family":"Ghazi","sequence":"first","affiliation":[{"name":"Google Research, Mountain View, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4296-2393","authenticated-orcid":true,"given":"Pritish","family":"Kamath","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2203-2586","authenticated-orcid":true,"given":"Ravi","family":"Kumar","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-2801","authenticated-orcid":true,"given":"Pasin","family":"Manurangsi","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3860-223X","authenticated-orcid":true,"given":"Adam","family":"Sealfon*","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","unstructured":"US Congress Public Law 94-171 (89 Stat. 1023) 94th Congress (1975) mandates the provision of small-area census data for the purpose of legislative redistricting."},{"key":"e_1_3_2_3_2","volume-title":"Counting for Dollars 2020: The Role of the Decennial Census in the Geographic Distribution of Federal Funds","author":"Reamer A.","year":"2020","unstructured":"A. Reamer, Counting for Dollars 2020: The Role of the Decennial Census in the Geographic Distribution of Federal Funds (GW Institute of Public Policy, George Washington Univ., 2020)."},{"key":"e_1_3_2_4_2","unstructured":"National Academies of Sciences Engineering and Medicine Census Data Field Guide for Transportation Applications (The National Academies Press) (2025); https:\/\/nap.nationalacademies.org\/catalog\/29028\/census-data-field-guide-for-transportation-applications."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.2105\/AJPH.2003.032482"},{"key":"e_1_3_2_6_2","first-page":"407","article-title":"Computational redistricting and the voting rights act. Election Law Journal: Rules","volume":"20","author":"Becker A.","year":"2021","unstructured":"A. Becker, M. Duchin, D. Gold, S. Hirsch, Computational redistricting and the voting rights act. Election Law Journal: Rules. Polit. Policy 20, 407\u2013441 (2021).","journal-title":"Polit. Policy"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1257\/aeri.20230459"},{"key":"e_1_3_2_8_2","unstructured":"US Code 13 U.S.C. \u00a7\u00a7 8\u20139 Title 13 US Code Sections 8 and 9 (2024) establishes the legal mandate for respondent confidentiality."},{"key":"e_1_3_2_9_2","unstructured":"J. M. Abowd Declaration of John M. Abowd Filed in State of Alabama v. Department of Commerce Case No. 3:21-cv-00211-RAH-ECM-KCN Document 41-1 (M.D. Alabama April 13 2021) (2021) https:\/\/vhdshf2oms2wcnsvk7sdv3so.blob.core.windows.net\/thearp-media\/documents\/Declaration_of_John_M._Abowd.pdf."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.4a1ebf70"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","unstructured":"C. Dwork F. McSherry K. Nissim A. D. Smith \u201cCalibrating Noise to Sensitivity in Private Data Analysis\u201d in Theory of Cryptography S. Halevi T. Rabin Eds. (Springer 2006) pp. 265\u2013284.","DOI":"10.1007\/11681878_14"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"J. M. Abowd \u201cThe U.S. Census Bureau Adopts Differential Privacy\u201d in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Association for Computing Machinery 2018) p. 2867.","DOI":"10.1145\/3219819.3226070"},{"key":"#cr-split#-e_1_3_2_13_2.1","unstructured":"J. M. Abowd R. Ashmead R. CumingsMenon S. Garfinkel M. Heineck C. Heiss R. Johns D. Kifer P. Leclerc A. Machanavajjhala B. Moran W. Sexton M. Spence P. Zhuravlev The 2020 Census Disclosure Avoidance System TopDown Algorithm. Harvard Data Science Review (Special Issue 2)"},{"key":"#cr-split#-e_1_3_2_13_2.2","doi-asserted-by":"crossref","unstructured":"https:\/\/doi.org\/10.1162\/99608f92.529e3cb9 (2022).","DOI":"10.1162\/99608f92.529e3cb9"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adl2524"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2003714117"},{"key":"e_1_3_2_16_2","unstructured":"C. L. Canonne G. Kamath T. Steinke \u201cThe discrete Gaussian for differential privacy\u201d in Advances in Neural Information Processing Systems H. Larochelle M. Ranzato R. Hadsell M. F. Balcan H. Lin Eds. (Curran Associates 2020) vol. 33 pp. 15676\u201315688."},{"key":"e_1_3_2_17_2","unstructured":"US Census Bureau Disclosure Avoidance and the 2020 Census: How the TopDown Algorithm Works 2020 Census Briefs C2020BR-04 US Department of Commerce US Census Bureau (2023); https:\/\/www2.census.gov\/library\/publications\/decennial\/2020\/census-briefs\/c2020br-04.pdf."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0370164600014346"},{"key":"e_1_3_2_19_2","unstructured":"R. Cumings-Menon P. Zhuravlev Least Squares Estimation For Hierarchical Data arXiv 2404.13164 (2025)."},{"key":"e_1_3_2_20_2","unstructured":"L. L. C. Gurobi Optimization Gurobi Optimizer Reference Manual (2026) https:\/\/www.gurobi.com."},{"key":"e_1_3_2_21_2","unstructured":"R. Ashmead M. B. Hawes M. Pritts P. Zhuravlev S. A. Keller An Approximate Monte Carlo Simulation Method for Estimating Uncertainty and Constructing Confidence Intervals for 2020 Census Statistics. arXiv 2503.19714 (2025)."},{"key":"e_1_3_2_22_2","unstructured":"US Census Bureau 2020 Census Disclosure Avoidance System Detailed Summary Metrics (2023); https:\/\/www.census.gov\/programs-surveys\/decennial-census\/decade\/2020\/planning-management\/process\/disclosure-avoidance\/protections-by-data-product.html."},{"key":"#cr-split#-e_1_3_2_23_2.1","unstructured":"US Census Bureau Estimating Confidence Intervals for 2020 Census Statistics Using Approximate Monte Carlo Simulation (2020 Census Production Run)"},{"key":"#cr-split#-e_1_3_2_23_2.2","unstructured":"(2024) https:\/\/registry.opendata.aws\/census-2020-amc-mdf-replicates\/."},{"key":"e_1_3_2_24_2","unstructured":"US Department of Commerce Disclosure Avoidance for Statistical Products Department Administrative Order (DAO) 216-26 US Department of Commerce (2026); https:\/\/www.commerce.gov\/opog\/disclosure-avoidance-statistical-products effective June 4 2026."},{"key":"e_1_3_2_25_2","unstructured":"J. Mervis Scientists attack ban on adding \u2018noise\u2019 to U.S. census data and many surveys. ScienceInsider (20 July 2026); https:\/\/www.science.org\/content\/article\/scientists-attack-ban-adding-noise-u-s-census-data-and-many-surveys."},{"key":"e_1_3_2_26_2","unstructured":"US Code 49 U.S.C. \u00a7 5336a Title 49 US Code Section 5336 (20264) establishes rules for apportionment of appropriations for grants."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2500337122"},{"key":"e_1_3_2_28_2","unstructured":"B. Ghazi P. Kamath R. Kumar P. Manurangsi A. Sealfon Replication Data for: Denoising the US Census: Succinct block hierarchical regression (2026); https:\/\/doi.org\/10.7910\/DVN\/JCZBBV."},{"key":"e_1_3_2_29_2","unstructured":"U.S. Census Bureau TIGER\/Line and Cartographic Boundary Shapefiles (2010 and 2020); https:\/\/www2.census.gov\/geo\/tiger\/."},{"key":"e_1_3_2_30_2","unstructured":"U.S. Census Bureau County Population Totals: 2010-2019 (2020); https:\/\/www2.census.gov\/programs-surveys\/popest\/datasets\/2010-2019\/counties\/totals\/co-est2019-alldata.csv."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1934-05899-3"},{"key":"e_1_3_2_32_2","volume-title":"Advanced Econometrics","author":"Amemiya T.","year":"1985","unstructured":"T. Amemiya, Advanced Econometrics (Harvard Univ. Press) (1985)."},{"key":"e_1_3_2_33_2","volume-title":"Convex Optimization","author":"Boyd S. P.","year":"2014","unstructured":"S. P. Boyd, L. Vandenberghe, Convex Optimization (Cambridge Univ. Press, 2014)."},{"key":"e_1_3_2_34_2","volume-title":"Matrix Analysis","author":"Horn R. A.","year":"2013","unstructured":"R. A. Horn, C. R. Johnson, Matrix Analysis (Cambridge Univ. Press, 2013)."},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"R. M. Karp Reducibility Among Combinatorial Problems in Proc. Symp. Complexity of Computer Computations The IBM Research Symposia Series (1972) pp. 85\u2013103.10.1007\/978-1-4684-2001-2_9","DOI":"10.1007\/978-1-4684-2001-2_9"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"M. Hay V. Rastogi G. Miklau D. Suciu \u201cBoosting the accuracy of differentially private histograms through consistency\u201d in Proceedings of the VLDB Endowment (2010) pp. 1021\u20131032.","DOI":"10.14778\/1920841.1920970"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"G. Cormode C. Procopiuc D. Srivastava E. Shen T. Yu \u201cDifferentially private spatial decompositions\u201d in IEEE 28th International Conference on Data Engineering (2012) pp. 20\u201331.","DOI":"10.1109\/ICDE.2012.16"},{"key":"e_1_3_2_38_2","unstructured":"J. Honaker Efficient use of differentially private binary trees. Theory and Practice of Differential Privacy (TPDP 2015) 2 26\u201327 (2015)."},{"key":"e_1_3_2_39_2","unstructured":"M. Dawson B. Ghazi P. Kamath K. Kumar R. Kumar B. L. Pasin Manurangsi N. Mundru H. Nair A. Sealfon S. Zhu \u201cOptimizing Hierarchical Queries for the Attribution Reporting API\u201d in AdKDD (2023)."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0398-x"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1137\/130938943"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"A. Edmonds A. Nikolov J. R. Ullman The power of factorization mechanisms in local and central differential privacy in STOC (2020) pp. 425\u2013438.","DOI":"10.1145\/3357713.3384297"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1093\/imrn\/rny033"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.791"},{"key":"e_1_3_2_45_2","unstructured":"A. Cohen M. Duchin J. Matthews B. Suwal \u201cCensus TopDown: The Impacts of Differential Privacy on Redistricting\u201d in 2nd Symposium on Foundations of Responsible Computing (FORC 2021)."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.22fd8a0e"},{"key":"e_1_3_2_47_2","unstructured":"J. Ko J. Ziani F. Fioretto Optimal Allocation of Privacy Budget on Hierarchical Data Release arXiv:2505.10871 [cs.CR] (2025)."}],"container-title":["Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/science.aej1765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T19:03:31Z","timestamp":1793905411000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/science.aej1765"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11,5]]},"references-count":48,"journal-issue":{"issue":"6824","published-print":{"date-parts":[[2026,11,5]]}},"alternative-id":["10.1126\/science.aej1765"],"URL":"https:\/\/doi.org\/10.1126\/science.aej1765","relation":{},"ISSN":["0036-8075","1095-9203"],"issn-type":[{"value":"0036-8075","type":"print"},{"value":"1095-9203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11,5]]},"assertion":[{"value":"2026-05-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-11-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}