Skip to content

CRiDiT: Instantiating a run-time testbed for trust calibration in AI-infused systems

Sep 2026 · arXiv.org · Vol abs/2609.24833 · 0 citations · 30 references
Computer Science

TL;DR

CRiDiT (Computational Risk-Sensitive biDirectional Trust) is instantiated as a run-time testbed, operationalising machine-side trust with Dempster-Shafer Theory and PCR5 redistribution, human-side trust with Subjective Logic, and calibration with a threshold-based trust gap.

Abstract

The integration of AI into larger technical infrastructures has made the alignment of human trust with system trustworthiness, known as trust calibration, a critical engineering concern, since misplaced trust in either direction leads to operational and safety risks. While conceptual frameworks provide a strong foundation for understanding trust calibration, their translation into running systems remains a challenge, because there are few testbeds in which human trust inputs, machine trustworthiness evidence, gap detection and remediation operate together within a closed loop. This paper instantiates CRiDiT (Computational Risk-Sensitive biDirectional Trust) as a run-time testbed, operationalising machine-side trust with Dempster-Shafer Theory and PCR5 redistribution, human-side trust with Subjective Logic, and calibration with a threshold-based trust gap. Following the Design Science Research methodology, we exercise the artifact across three high-stakes scenarios (hiring, financial, legal), producing 144 logged interaction steps across fifteen sessions. The analysis shows that the artifact captures trust calibration dynamics as intended, and reveals three points at which the instantiated policy departs from its design requirements: the machine-side estimate begins from a global benchmark rather than task-relevant evidence; risk-sensitive thresholds do not produce risk-sensitive triggering; and the calibration policy assigns explanatory prompts to over-trust, where corrections narrowed the gap in all 6 observed cases. Since the first two arise from the same design decision, to make the difference of two estimated scalars the calibration criterion, they point toward a common requirement: that the criterion should operate on the evidence rather than on scalars derived from it. The third concerns what follows detection, and shows that the action vocabulary inherited from trust repair does not align with what the interaction logs show to be effective. The work contributes the artifact, a characterisation of its run-time behaviour, and the requirements this characterisation elicits.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Trust Hinders Bidirectional Human-AI Alignment

Trust calibration remains the dominant framing of AI-assisted decision making: the goal is to close the gap between perceived and actual trustworthiness of AI systems so that users rely on them appropriately. We argue that this approach, while useful for decision problems that are well-defined and clearly scoped, overl...

Michaela Benk, Kacper Sokol · 0 citations
Open access Sep 2026

Trust inversion and its exploitation: A threat model of the Model Context Protocol for agentic AI

The analysis groups risks into descriptor and capability drift, cross-tool trust propagation, and sampling-mediated server influence, while separating protocol, ecosystem, implementation, and deployment weaknesses.

M. Q. Sambo, Augustine Yusuf, I. Nwokoro et al. · 0 citations
Open access Oct 2026

Event-Anchored Trust in AI-Powered Assessment: Why Trust Collapses Faster than It Repairs

Trust in AI-powered grading systems can shatter overnight after a single disputed score, yet rebuilding that trust takes months. This paper develops a framework to explain this “fast-collapse, slow-repair” asymmetry. We introduce Event-Anchored Trust (EAT), reconceptualizing trust as an event-contingent judgment rather...

Hui-Jia Zhang · 0 citations
#explainable ai Review Open access Oct 2026

Agentic AI-Driven SOC-as-a-Service for Optimizing Incident Response in Cloud Environments: A Conceptual Framework

Cloud security operations must process high-volume, rapidly changing telemetry within short response windows while maintaining governance and accountability. However, the literature on cloud defense, SOC modernization, retrieval-augmented generation (RAG), and Agentic AI remains fragmented. This paper combines a legacy...

Abdulaziz Y. Alhumaidi, Faisal A. Al-Qadda, Albandari Alsumayt et al. · 0 citations
Conference Open access Oct 2026

Five Obstacles to AI Trustworthiness Alignment and How to Deal with Them: Introducing the DELIB-TRUST Framework

Aligning the perceived trustworthiness and trusting behavior of users with the capabilities and characteristics of AI systems is considered central to the adoption of AI systems in society. However, achieving such a trustworthiness alignment faces major practical obstacles, at least with more complex notions of trust t...

Pascal D. Koenig, Siddharth Mehrotra · 0 citations
Book Open access Oct 2026

Compliance Won't Save Trust. What Seven Years of AI and Privacy Research Taught Us

Findings from a seven-year industry research program conducted across twelve countries, comprising over sixty qualitative studies including in-home interviews, diary studies, and prototype evaluations, are presented, showing that trust is not a fixed attribute but a dynamic process shaped by everyday interactions.

Camilla Pia Warmedinger, Yoel Lenti Berrospi · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Putting a spotlight on AI, society, and humanity

Supported by the MIT Human Insight Collaborative, scholars are exploring how AI is impacting the human experience and reshaping higher education.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.