The Chain Behind the Claim: Warrantability in AI-Assisted Qualitative Research

AbstractLarge language models allow education researchers to reorganize qualitative corpora in minutes, producing fluent topics, quotations, and prevalence claims. Fluent output can conceal the analytic pathway that produced it. Extending the field’s evidence debates and the audit-trail tradition into the generative era, this essay proposes warrantability as a standard that complements accuracy and disclosure. An AI-assisted interpretation is warrantable when the pathway from source data to claim remains inspectable, contestable, and revisable. I introduce semantic lenses, documented reorganizations of a corpus across levels of abstraction, and a claim-relative repertoire of warrant artifacts, from source-linked topic tables to lens stacks and evidence rivers, that make different inferential moves available for examination. Designed into research tools, these representations can strengthen peer review and widen access to accountable AI-assisted inquiry.