Understanding: reframing automation and assurance

• URL: http://arxiv.org/abs/2604.05662v1
• Date: Tue, 07 Apr 2026 10:04:26 GMT
• Title: Understanding: reframing automation and assurance
• Abstract summary: Safety and assurance cases risk becoming detached from the understanding needed for responsible engineering and governance decisions.<n>We argue that understanding should become an explicit, assessable, and defensible component of decision making.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safety and assurance cases risk becoming detached from the understanding needed for responsible engineering and governance decisions. More broadly, the production and evaluation of critical socio-technical systems increasingly face an understanding challenge: pressures for increased tempo, reduced scrutiny, software complexity, and growing use of AI generated artefacts may produce outputs that appear coherent without supporting genuine human comprehension. We argue that understanding should become an explicit, assessable, and defensible component of decision making: what developers, assessors, and decision makers grasp about system behavior, evidence, assumptions, risks, and residual uncertainty. Drawing on Catherine Elgin's epistemology of understanding, we outline a conceptual foundation and then use Assurance 2.0 as an engineering route to operationalize using structured argumentation, evidence, confidence, defeaters, and theory based automation. This leads to two linked artefacts: an Understanding Basis, which justifies why available understanding is sufficient for a decision, and a Personal Understanding Statement, through which participants make their grasp explicit and challengeable. We also identify risks that automation may improve artefact production while weakening understanding, and we propose initial directions for evaluating both efficacy and epistemic impact.

Related papers

• Understanding as an Explicit and Assessable Component of Frontier AI Safety Decisions [35.25345433558124]
  Decision makers need sufficient understanding to make good decisions about training or deploying frontier AI systems.<n>This paper builds on recent developments in safety cases using the Assurance 2.0 framework to operationalise the philosophical basis of understanding from Elgin and Arendt.
  arXiv  Detail & Related papers  (2026-08-20T09:12:36Z)
• The Ethical Knowledge Gap: Dispersed Knowledge, Sensemaking Failures, and Epistemic Dependence [0.0]
  This paper argues that the persistent gap between ethical intention and ethical implementation is a structural condition.<n>Ethical software development remains stubbornly difficult despite two decades of normative frameworks, professional codes, and participatory methodologies.
  arXiv  Detail & Related papers  (2026-04-27T08:16:16Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• AI Deception: Risks, Dynamics, and Controls [153.71048309527225]
  This project provides a comprehensive and up-to-date overview of the AI deception field.<n>We identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception.<n>We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment.
  arXiv  Detail & Related papers  (2025-11-27T16:56:04Z)
• Hybrid Reasoning for Perception, Explanation, and Autonomous Action in Manufacturing [0.0]
  CIPHER is a vision-language-action (VLA) model framework aiming to replicate human-like reasoning for industrial control.<n>It integrates a process expert, a regression model enabling quantitative characterization of system states.<n>It interprets visual or textual inputs from process monitoring, explains its decisions, and autonomously generates precise machine instructions.
  arXiv  Detail & Related papers  (2025-06-10T05:37:33Z)
• A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems [93.8285345915925]
  Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making.<n>With the rapid advancement of large language models (LLMs), reasoning has emerged as a key capability that distinguishes advanced AI systems.<n>We categorize existing methods along two dimensions: (1) Regimes, which define the stage at which reasoning is achieved; and (2) Architectures, which determine the components involved in the reasoning process.
  arXiv  Detail & Related papers  (2025-04-12T01:27:49Z)
• AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons [62.374792825813394]
  This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability.<n>The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories.
  arXiv  Detail & Related papers  (2025-02-19T05:58:52Z)
• Mechanistic Interpretability for AI Safety -- A Review [28.427951836334188]
  This review explores mechanistic interpretability. Mechanistic interpretability could help prevent catastrophic outcomes as AI systems become more powerful and inscrutable.
  arXiv  Detail & Related papers  (2024-04-22T11:01:51Z)
• Trustworthy, responsible, ethical AI in manufacturing and supply chains: synthesis and emerging research questions [59.34177693293227]
  We explore the applicability of responsible, ethical, and trustworthy AI within the context of manufacturing. We then use a broadened adaptation of a machine learning lifecycle to discuss, through the use of illustrative examples, how each step may result in a given AI trustworthiness concern.
  arXiv  Detail & Related papers  (2023-05-19T10:43:06Z)
• Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
  We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
  arXiv  Detail & Related papers  (2020-03-09T15:04:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.