Ceci n'est pas une pipe: AI systems as semantic abstractions
2026-07-10 • Artificial Intelligence
Artificial IntelligenceProgramming Languages
AI summaryⓘ
The authors explain that an AI's responses are not direct facts but are carefully created representations. They suggest a way to understand and check how these AI outputs relate to real knowledge, sources, and what the AI can actually use. Their method helps clearly define common mistakes like using outdated information or making unsupported claims. This framework aims to help ensure AI outputs are backed by reliable evidence rather than just sounding convincing.
AI outputsemantic frameworkdomain knowledgereference sourcesextrapolationassertionknowledge mismatchhypothesesjustificationauthority
Authors
Jade Alglave, Patrick Cousot
Abstract
An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation. We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations. To do so, we distinguish what is justified by accepted domain knowledge, what reference sources say, and what the system can currently use. This allows us to give precise definitions to common failures: extrapolation, refuted or unsupported assertion, sources versus knowledge mismatch, stale or refuted source, added hypotheses, unsupported use... We hope our framework gives a useful vocabulary for specifying and checking AI systems whose outputs, citations, tool calls, and world-changing actions must be justified by reliable claims and explicit authority rather than apparent fluency.