JustDiag!: A Diagnostic Justification Engine for Accountable Root Cause Analysis

A new diagnostic justification engine called JustDiag has been developed to make root cause analysis more accountable by requiring explicit evidence trails rather than relying solely on fluent final answers from large language models [1][2]. The system, described in a paper submitted to arXiv on June 17, 2026, maintains an explicit process state that tracks evidence, findings, competing hypotheses, conflicts, and next checks during incident investigations [2]. Researchers evaluated JustDiag on 66 real-world incidents using a two-layer protocol that separately scores final-answer quality and process quality [2]. Relative to a matched control system without diagnostic justification capabilities, JustDiag achieved stronger outcome and process scores [2]. The system accepted slightly lower terminal completion rates due to what the researchers describe as more calibrated non-closure, meaning it preserved uncertainty rather than forcing a definitive answer when evidence was insufficient [2]. The work addresses a gap identified by the authors: large language models can produce fluent root cause analyses, but fluent final answers alone are insufficient evidence for accountability in high-stakes operations [2]. In real incident response, engineers need to know what evidence supported a diagnosis, which alternatives were considered, where contradictions remained, and whether the system resolved the case or preserved uncertainty [2]. The paper appears on arXiv, the open-access repository of electronic preprints that began on August 14, 1991, and now hosts over two million articles across mathematics, physics, computer science, and other fields [6]. As of November 2024, the repository receives approximately 24,000 submissions per month [6]. The research is accessible through arXivLabs, a framework launched in 2020 that enables community collaborators to develop and share experimental tools directly on the arXiv website [4]. "Members of our community want to contribute tools that enhance the arXiv experience, and we value that kind of community engagement," said Eleonora Presani, arXiv Executive Director, at the framework's launch [4]. The arXivLabs framework sets guidelines ensuring that partners share arXiv's values of openness, community, excellence, and user data privacy [4]. The researchers conclude that accountable root cause analysis requires explicit diagnostic justification artifacts and process-aware evaluation, not only fluent final answers [2].