---
title: "Authoring and Management of Transparent Research Integrity Assessments of Randomised Clinical Trial Publications Using LLM-assisted Tools and Provenance Knowledge Graphs"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.07202v1"
permalink: "https://feed.astralor.com/items/itm_1af1ff0ee98e97cb4d70b73d"
published: "2026-08-07T13:17:56.000Z"
score: 72
channel: "tech"
tags: ["INSPECT-AI","LLM","Knowledge Graph","Research Integrity"]
---

# Authoring and Management of Transparent Research Integrity Assessments of Randomised Clinical Trial Publications Using LLM-assisted Tools and Provenance Knowledge Graphs

## AI commentary

> This study offers an AI-assisted solution for medical evidence review, valuable for researchers in medical informatics, clinical research methodology, and LLM applications. Although currently a preprint, the RIPE-KG dataset could serve as a foundation for future research.

## At a glance

This paper introduces INSPECT-AI, an LLM-based interactive tool that assists human reviewers in assessing the research integrity of published randomised controlled trials (RCTs) according to the INSPECT-SR framework, and the RIPE-O ontology for documenting the provenance of the assessment process. The authors also present RIPE-KG, a knowledge graph containing 140 expert research integrity assessments of 95 RCT publications, generated using INSPECT-AI and described with RIPE-O. This work aims to improve the reliability and transparency of evidence used in systematic reviews and clinical guidelines.

## Key points

- INSPECT-AI combines LLMs with provenance knowledge graphs to assist human reviewers in RCT research integrity assessment.
- The RIPE-O ontology is used to document provenance of the assessment process, enhancing transparency.
- RIPE-KG contains 140 expert assessments covering 95 RCT publications.
- It aims to reduce manual review burden and improve consistency and evidence quality.

## Full text

Systematic reviews of Randomised Controlled Trials (RCTs) are routinely used as evidence for clinical care guidelines. Such evidence has to meet high research integrity standards to prevent low quality or false research outputs influencing the clinical care. However, assessing research integrity of published RCTs is a complex process requiring manual effort, and potentially resulting in diverse opinions of the human assessors. This paper describes INSPECT-AI, an LLM-based interactive tool that assists human reviewers with research integrity assessments of published RCTs based on the community approved INSPECT-SR framework, and the Research Integrity Provenance and Evidence ontology (RIPE-O) for documenting the provenance of the assessment process. In addition, we present the Research Integrity Provenance and Evidence knowledge graph (RIPE-KG), an initial set of 140 expert research integrity assessments of 95 RCT publications generated by INSPECT-AI and described using RIPE-O.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_1af1ff0ee98e97cb4d70b73d