Newest papers

Contestable Agents for Data Governance: Recording Human Stewardship of AI-Generated Metadata Across Structured and Unstructured Systems

Humza Akhtar, Brian Freeman · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31553 · cited by 0 works (OpenAlex) · open-access PDF

Korean

산업 조직은 구조화된 레코드, 포인트리스트, 거래와 같은 필드 레코드에서 운영 지식을 보유하고 있으며, 매뉴얼, 서비스 노트, 통신 및 검사 보고서와 같은 구조화되지 않은 소스에서 운영 지식을 보유합니다. 통제 프로그램은 종종 별도로 이러한 소스를 관리합니다. 분류, 링크 및 문서화는 깊은 도메인 지식이있는 직원의 소규모 그룹에 의존합니다. 대리인은 대화 된 메타데이터 결정에 대한 포인트를 제안하고, 문서를 인용하고, 깃발 품질 문제를 언급 할 수 있지만, 검토되지 않은 제안은 아래 시스템에 오류를 퍼뜨릴 수 있습니다. perfunctory 승인은 리뷰가 검사 한 것에 대한 기록을 남기지 않습니다. 우리는 논란의 여지가있는 통

Machine translation (Meta M2M100); the English original follows.

Abstract

Industrial organizations hold operational knowledge in structured records, such as telemetry, point lists, and transactions, and in unstructured sources, such as manuals, service notes, communications, and inspection reports. Governance programs often manage these sources separately. Classifying, linking, and documenting them depends on a small group of employees with deep domain knowledge. Agents built on large language models can propose metadata, cite documents, and flag quality issues, but unreviewed proposals can spread errors into downstream systems. A perfunctory approval leaves no record of what a reviewer checked. We present contestable governance: specialist agents produce scored, cited arguments for disputed metadata decisions; a steward can accept, reject, modify, or add arguments before commit; and a governance record retains the evidence, interventions, and outcome. A versioned domain glossary supplies model-specific terms and acronym definitions to the agents. We describe the workflow, a triage path that reserves full argumentation for uncertain proposals while preserving review before commit, the scoring and record models, and a gate that controls which verified decisions become precedent. Two HVAC use cases illustrate the pattern: point classification using Brick Schema class labels, supported by an open reference implementation, and an illustrative warranty failure-mode decision linking claim fields and telemetry to service notes and revisioned bulletins.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Metadata, Service (business), Data science, Corporate governance, Computer security

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31553, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange