paper-with-me

홈 › Papers

The Competence Shadow: Theory and Bounds of AI Assistance in Safety Engineering

2026-03-26 · Umair Siddique arxiv

As AI assistants become integrated into safety engineering workflows for Physical AI systems, a critical question emerges: does AI assistance improve safety analysis quality, or introduce systematic blind spots that surface only through post-deployment incidents? This paper develops a formal framework for AI assistance in safety analysis. We first establish why safety engineering resists benchmark-driven evaluation: safety competence is irreducibly multidimensional, constrained by context-dependent correctness, inherent incompleteness, and legitimate expert disagreement. We formalize this through a five-dimensional competence framework capturing domain knowledge, standards expertise, operational experience, contextual understanding, and judgment. We introduce the competence shadow: the systematic narrowing of human reasoning induced by AI-generated safety analysis. The shadow is not what the AI presents, but what it prevents from being considered. We formalize four canonical human-AI collaboration structures and derive closed-form performance bounds, demonstrating that the competence shadow compounds multiplicatively to produce degradation far exceeding naive additive estimates. The central finding is that AI assistance in safety engineering is a collaboration design problem, not a software procurement decision. The same tool degrades or improves analysis quality depending entirely on how it is used. We derive non-degradation conditions for shadow-resistant workflows and call for a shift from tool qualification toward workflow qualification for trustworthy Physical AI.

📄 PDF Abstract BibTeX arXiv:2603.25197

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How AI Impacts Skill Formation

2026-01-28 · Judy Hanwen Shen, Alex Tamkin arxiv

AI assistance produces significant productivity gains across professional domains, particularly for novice workers. Yet how this assistance affects the development of skills required to effectively supervise AI remains u…

Learning to Optimize Autonomy in Competence-Aware Systems

2020-03-17 · Connor Basich, Justin Svegliato, Kyle Hollins Wray, Stefan Witwicki 외

Interest in semi-autonomous systems (SAS) is growing rapidly as a paradigm to deploy autonomous systems in domains that require occasional reliance on humans. This paradigm allows service robots or autonomous vehicles to…

Autonomous DrivingAutonomous Vehicles

Online learning of quantum processes

2024-06-06 · Asad Raza, Matthias C. Caro, Jens Eisert, Sumeet Khatri

Among recent insights into learning quantum states, online learning and shadow tomography procedures are notable for their ability to accurately predict expectation values even of adaptively chosen observables. In contra…

Consistency of weighted majority votes

2013-12-02 · NeurIPS 2014 12 · Daniel Berend, Aryeh Kontorovich

We revisit the classical decision-theoretic problem of weighted expert voting from a statistical learning perspective. In particular, we examine the consistency (both asymptotic and finitary) of the optimal Nitzan-Parous…

Curriculum Learning for Safety Alignment

2026-05-25 · Sandeep Kumar, Virginia Smith, Chhavi Yadav arxiv

Direct Preference Optimisation (DPO) is widely used for safety alignment in large language models. However, prior work shows it is brittle and exhibits poor out-of-distribution (OOD) generalisation. In this paper, we inv…