Newest papers

Reusing Assurance Evidence in AI Pipelines: Validity Conditions, a Fail-Closed Release Gate, and a Replay of 714 Public Data Version Control Pipelines

Atanu Mukhopadhyay, Shravya Reddy Nalla · 2026 · arXiv

DOI: 10.48550/arXiv.2610.27672 · open-access PDF

Korean

인공 지능 (AI) 파이프 라인에 대한 모든 변경 후 모든 통제 제어를 재사용하는 것은 비싸기 때문에 팀이 이전 결과를 재사용합니다. 재사용은 각 컨트롤의 선언 된 의존성이 결과를 변경할 수있는 모든 것을 다루는 경우에만 안전하며, 재사용 증거가 발표되는 후보를 설명하는 릴리스 게이트 체크만 경우에만 안전합니다.이 문서는 두 조건을 명시하고 첫 번째가 실제로 실패하는 횟수를 측정합니다.이 문서는 서명된 증거 기록이 후보에게 유효한 때를 정의하고 변경-지역 재사용이 동일한 릴리스에 도달하는 충분한 조건을 제공합니다.

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

Abstract

Rerunning every governance control after every change to an artificial intelligence (AI) pipeline is expensive, so teams reuse earlier results. Reuse is safe only if each control's declared dependencies cover everything that can change its outcome, and only if the release gate checks that reused evidence describes the candidate being released. This article makes both conditions explicit and measures how often the first fails in practice. It defines when a signed evidence record is valid for a candidate and gives sufficient conditions under which change-local re-execution reaches the same relea

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

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=2610.27672, 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