Empirical effect of semantic persistence on audit quality and trust

Determine whether representing consequential workflow artifacts as typed, contextualized, and dependency-linked persistent records improves audit quality or trust in practice.

Background

The proposed model claims that explicit types, context snapshots, identities, and dependency relations can make workflow history and mediated judgments more reviewable. However, the paper does not empirically establish that these affordances improve audit quality or trust; the authors explicitly classify this relationship as an empirical question requiring future evaluation.

References

The resulting research agenda connects application analysis, interface design, controlled execution, and quality assessment. Contrasting examples in collaboration, spreadsheets, integrated development environments (IDEs), and service consoles examine the scope of the argument. The contribution is a conceptual framework with conditional reasoning and worked examples; its practical benefits remain questions for comparative engineering and human studies.

— Agent-Integrated Software: Interaction Contracts and Continuous Assurance  (2609.11381 - Yu et al., 10 Sep 2026) in Section 1, Introduction; Section 6.3, “What Would Establish the Value of This Perspective?”

Future evaluation should establish whether the Data Hospital can support a complete data-quality task without obscuring the distinction between technical evidence, contextual judgment, user decisions, and resulting data states. It should also test whether documentation and replay remain consistent with the interventions that were actually performed.

— The Data Hospital: A Workflow-Based Concept for Explainable Research Data Quality Assistance  (2609.20782 - Scheurer et al., 17 Sep 2026) in Section 5.1, “Evaluation Goals” (Planned Evaluation and Research Agenda)

Whether these affordances improve audit quality or trust in practice is an empirical question, not a claim of this paper.

— Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows  (2607.08740 - Quinto et al., 9 Jul 2026) in Section 5, “Discussion And Limits”

A versioned dependency and evidence graph is a candidate shared abstraction for invalidation, regression, rollback, and renewed review, but current cross-family evidence is too sparse to establish one mechanism.

— Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities  (2608.28122 - Wang et al., 28 Aug 2026) in Section 7.4, Revalidate Affected State

Whether such provenance is comprehensible, useful, or burdensome remains an empirical question.

— Beyond Prompt-to-App: Accountable Translation in Teacher-Facing Agentic Authoring  (2609.04679 - Kadir et al., 4 Sep 2026) in Section 6.3, “Proposition: semantic diffs can make handoffs inspectable”