{"paper":{"title":"Tradeoffs are Domain Dependent: Improving Accuracy and Fairness in Property Tax Assessments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"In U.S. property tax assessments, accuracy and fairness improve together with better models and data, rather than trading off against each other.","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Christopher Berry, Daniel E. Ho, Emma Harvey, Evelyn Smith, Jacob Goldin","submitted_at":"2026-05-14T16:20:32Z","abstract_excerpt":"Algorithmic fairness research often assumes a tradeoff between fairness and accuracy. Yet this tradeoff may not be universal. We test this assumption in the context of U.S. property tax assessment - a setting in which the output of predictive algorithms directly determines the distribution of tax obligations among homeowners. Currently, systematic assessment errors cause owners of lower-valued properties to face disproportionately high tax burdens, creating regressivity in the property tax system. Using data on 26 million property sales spanning 95% of U.S. counties, we conduct three complemen"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"we show that incorporating publicly available Census data into assessment models - a feasible reform in most counties - would significantly improve both accuracy and fairness relative to status quo assessments.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the simulated assessment models and domain-relevant fairness metrics accurately reflect real-world implementation effects and capture the intended notions of fairness in tax burdens.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"In U.S. property tax assessments, accuracy and fairness improve together with better models and data, rather than trading off against each other.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"137e23f79b83ae4b63ec742f786938f31a373c5fb7edffc7dce57a6f84080999"},"source":{"id":"2605.15020","kind":"arxiv","version":1},"verdict":{"id":"71c7cafe-7d1b-4383-a791-050d8f9a0ffd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:20:36.282326Z","strongest_claim":"we show that incorporating publicly available Census data into assessment models - a feasible reform in most counties - would significantly improve both accuracy and fairness relative to status quo assessments.","one_line_summary":"In U.S. property tax assessments, accuracy and fairness improve together with better models and data, rather than trading off against each other.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the simulated assessment models and domain-relevant fairness metrics accurately reflect real-world implementation effects and capture the intended notions of fairness in tax burdens.","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}