AI 生成研究成果如何核查：一个“先信任再验证、审计与归因”的人在回路框架

View PDF HTML (experimental)

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.

Comments:	17 pages, 3 figures, 5 tables. Skill files and run record: this https URL
Subjects:	Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Logic in Computer Science (cs.LO)
Cite as:	arXiv:2611.13042 [cs.AI]
	(or arXiv:2611.13042v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2611.13042 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Patrik P. Suli [view email]
[v1] Mon, 9 Nov 2026 11:58:29 UTC (24 KB)