cs.AINov 9, 2026

Trust, but verify, audit and attribute: a human-in-the-loop framework for checking AI-produced research results

Authors: György Eigner, Patrik P. Süli, Roland Hollós

Organizations: Biomatics and Applied Artificial Intelligence Institute, John von Neumann Faculty of Informatics, Obuda University, Budapest, Hungary · Physiological Controls Research Center, Obuda University, Budapest, Hungary · Doctoral School of Applied Informatics and Applied Mathematics, Obuda University, Budapest, Hungary · HUN-REN Centre for Agricultural Research, Brunszvik u. 2., 2462 Martonvásár, Hungary

Abstract

Artificial intelligence (AI) systems now produce research results in bulk: in October 2026 a single laboratory released more than 700 AI-generated mathematics manuscripts, only part of them with machine-checked proofs. Such volumes will be checked mostly by AI agents that call specialised software. A passing check certifies only the artefact that was checked. For proofs translated into the proof assistant Lean, it has been shown that this artefact may state something other than the author's text, and that deciding whether a translation is faithful is undecidable in general. The human researcher therefore stays in the loop, and human and AI contributions must be recorded. We propose a domain-independent, human-in-the-loop framework for checking AI-produced results. Validated, agent-usable tools with different grounds of trust check the results; a fidelity audit asks whether each check addressed the claim as stated; the human decides at fixed points; and a dialog report attributes the work to the human and to the AI. We describe two automatic implementations of the tool layer, for mathematics (Wolfram Language, MATLAB, Lean) and statistics (Python and R), and run the mathematical one on a two-claim example. An ambiguous claim was split into two readings, one refuted and one proved.

Figures & tables

Explore similar work

CardsList
  1. Beyond fabrication: Misattributed numbers in papers written by AI research agents

    Oct 28, 2026Mosab Alfaqeeh, Omar Mohammed Horani, Mou'th Hourani +1Claim VerificationAI Agent Auditing