Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure
2026-04-13 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors point out that AI systems using company knowledge often mix up facts with guesses or disagreements. They created OIDA, a system that organizes knowledge by showing how certain or uncertain each piece is and marking contradictions clearly. OIDA also highlights questions the organization hasn't answered yet, which helps show what is truly unknown. Their tests show OIDA works well at tracking knowledge quality, especially given limits on how much information can be processed at once.
Organizational KnowledgeEpistemic FidelityKnowledge ObjectsContradiction EdgesKnowledge Gravity EngineQUESTION-as-modeled-ignoranceEpistemic Quality ScoreRetrieval-Augmented Generation (RAG)Token BudgetFisher Exact Test
Authors
Federico Bottino, Carlo Ferrero, Nicholas Dosio, Pierfrancesco Beneventano
Abstract
Organizational knowledge used by AI agents typically lacks epistemic structure: retrieval systems surface semantically relevant content without distinguishing binding decisions from abandoned hypotheses, contested claims from settled ones, or known facts from unresolved questions. We argue that the ceiling on organizational AI is not retrieval fidelity but \emph{epistemic} fidelity--the system's ability to represent commitment strength, contradiction status, and organizational ignorance as computable properties. We present OIDA, a framework that structures organizational knowledge as typed Knowledge Objects carrying epistemic class, importance scores with class-specific decay, and signed contradiction edges. The Knowledge Gravity Engine maintains scores deterministically with proved convergence guarantees (sufficient condition: max degree $< 7$; empirically robust to degree 43). OIDA introduces QUESTION-as-modeled-ignorance: a primitive with inverse decay that surfaces what an organization does \emph{not} know with increasing urgency--a mechanism absent from all surveyed systems. We describe the Epistemic Quality Score (EQS), a five-component evaluation methodology with explicit circularity analysis. In a controlled comparison ($n{=}10$ response pairs), OIDA's RAG condition (3,868 tokens) achieves EQS 0.530 vs.\ 0.848 for a full-context baseline (108,687 tokens); the $28.1\times$ token budget difference is the primary confound. The QUESTION mechanism is statistically validated (Fisher $p{=}0.0325$, OR$=21.0$). The formal properties are established; the decisive ablation at equal token budget (E4) is pre-registered and not yet run.