Guardado en:
Detalles Bibliográficos
Autores principales: Sunny, Allen Daniel, Sivan-Sevilla, Ido
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.12109
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909017907920896
author Sunny, Allen Daniel
Sivan-Sevilla, Ido
author_facet Sunny, Allen Daniel
Sivan-Sevilla, Ido
contents Automated eligibility systems increasingly determine access to essential public benefits, but the explanations they generate often fail to reflect the legal rules that authorize those decisions. This thesis develops a legally grounded explainability framework that links system-generated decision justifications to the statutory constraints of CalFresh, California's Supplemental Nutrition Assistance Program. The framework combines a structured ontology of eligibility requirements derived from the state's Manual of Policies and Procedures (MPP), a rule extraction pipeline that expresses statutory logic in a verifiable formal representation, and a solver-based reasoning layer to evaluate whether the explanation aligns with governing law. Case evaluations demonstrate the framework's ability to detect legally inconsistent explanations, highlight violated eligibility rules, and support procedural accountability by making the basis of automated determinations traceable and contestable.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12109
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Neuro-Symbolic Framework for Accountability in Public-Sector AI
Sunny, Allen Daniel
Sivan-Sevilla, Ido
Computers and Society
Artificial Intelligence
Logic in Computer Science
I.2.4; J.1; K.5.2
Automated eligibility systems increasingly determine access to essential public benefits, but the explanations they generate often fail to reflect the legal rules that authorize those decisions. This thesis develops a legally grounded explainability framework that links system-generated decision justifications to the statutory constraints of CalFresh, California's Supplemental Nutrition Assistance Program. The framework combines a structured ontology of eligibility requirements derived from the state's Manual of Policies and Procedures (MPP), a rule extraction pipeline that expresses statutory logic in a verifiable formal representation, and a solver-based reasoning layer to evaluate whether the explanation aligns with governing law. Case evaluations demonstrate the framework's ability to detect legally inconsistent explanations, highlight violated eligibility rules, and support procedural accountability by making the basis of automated determinations traceable and contestable.
title A Neuro-Symbolic Framework for Accountability in Public-Sector AI
topic Computers and Society
Artificial Intelligence
Logic in Computer Science
I.2.4; J.1; K.5.2
url https://arxiv.org/abs/2512.12109