The Replication Engine is an AI system that the Institute for Replication (I4R) is developing to check published research automatically, by reproducing a paper’s computational results, looking for coding errors and testing whether the main findings hold under robustness checks. Abel Brodeur, chair of I4R, and Bruno Barbarioli proposed it in August 2025 in a
The Replication Engine Read More »
FutureHouse is a philanthropically funded project building semi-autonomous AI for scientific research. It describes an AI Scientist as one that repeatedly builds a model of a problem, generates hypotheses, tests them and updates the model, working under a broad research direction set by a human. On 1 May 2025 it launched a platform, free to
FutureHouse AI Scientist Read More »
Abdulqadir J Nashwan of Hamad Medical Corporation, Qatar, published this editorial in the World Journal of Methodology on 20 March 2025. It proposes that data analysis, pattern recognition and natural language processing could help identify conflicts of interest by scanning research papers, grant proposals and related documents, by linking publication, funding and institutional records to
Harnessing artificial intelligence for identifying conflicts of interest in research Read More »
Deep Background is a prompt written by Mike Caulfield for use with Claude or ChatGPT, which he calls a contextualisation prompt and which is also known as the SIFT Toolbox. The model searches for conflicting sources, sorts the evidence using a Toulmin argument framework and produces structured reports covering verified facts, errors and corrections, source
Deep Background (SIFT Toolbox) Read More »
The STM Integrity Hub is a cloud-based environment, developed by STM Solutions, in which publishers screen submitted manuscripts for signs of paper mills and other research integrity concerns. STM launched it in May 2022. It passes submission data from journals and editorial systems to screening tools, gives members a space to build tools together, and
ARTEMIS is a web application developed by the ResearchHub Foundation that uses AI agents, an AI Editor and AI Peer Reviewers, to review scientific manuscripts. Jeffrey Koury and Dominikus Brian published a ResearchHub post about it on 27 February 2025. Scalene, Chris Leonard’s newsletter on peer review, reported on 10 March 2025 that ResearchHub had
ARTEMIS – Automated review and trustworthy evaluation for manuscripts in science Read More »
ReviewFlow is an AI-driven workflow for novice peer reviewers, developed by Lu Sun, Aaron Chan, Yun Seo Chang and Steven P. Dow after a formative study of 10 novice and 10 expert reviewers. It prompts novices with contextual reflection questions as they critique and annotate papers, gives in-situ support for judging novelty, and turns their
ReviewRobot is a system from Qingyun Wang, Qi Zeng, Lifu Huang, Kevin Knight, Heng Ji and Nazneen Fatema Rajani that assigns a review score and writes comments for review categories such as novelty and comparison with prior work. It builds knowledge graphs from the paper under review, the papers it cites and a broad collection
In February 2023 Matthew Brodhead, an associate professor at Michigan State University, asked ChatGPT to write an editorial decision letter for a paper that both reviewers had recommended rejecting, with the editor agreeing, and posted the result on LinkedIn. The letter thanks the author, gives the decision, leaves places for the reviewers’ comments and suggests
ChatGPT-generated editorial decision letter Read More »
OpenAIReview is an open-source, AI-assisted tool for reviewing academic papers, built by Chenhao Tan’s team at the Chicago Human+AI (CHAI) Lab, part of the University of Chicago Data Science Institute, to give any researcher paper feedback “for less than the cost of a coffee”. It processes a paper sequentially and keeps a running summary of
JAIGP is an open-access journal for AI-generated research in any field, founded by César Hidalgo, in which people prompt the AI systems that write the papers. Each paper names the AI model used and gives a “Prompted by” credit to a human. Submissions are screened by AI, endorsed by a verified scholar and reviewed by
JAIGP (Journal for AI Generated Papers) Read More »
The Agentic Reviewer is a free tool at paperreview.ai from the Stanford ML Group, built by Yixing Jiang and Andrew Ng and released in November 2025, that gives research papers AI-generated review feedback grounded in related arXiv papers. Users upload a PDF of up to 10MB, of which the first 15 pages are analysed, and
Stanford Agentic Reviewer Read More »
Paper2Agent is an open-source system from researchers at Stanford University, including Jiacheng Miao and James Zou, that turns a research paper and its code into an AI agent. It runs the code’s tutorials and builds a Model Context Protocol (MCP) server that chat agents such as Claude Code can load, so a user can ask
The LLM Citation Verifier is an open-source plugin by DWFlanagan for the LLM command-line tool that checks academic citations against the Crossref database while a model is generating text. The model calls a verify_citation tool with a DOI, and the tool returns whether the DOI exists in Crossref, with the title, authors, journal and year
LLM Citation Verifier Read More »
Metacheck is an open-source R package that checks research outputs for best practices, using text search, R code and, optionally, queries to large language models. Its 26 modules cover areas such as preregistrations, ethics approval, funding and conflict-of-interest statements, open practices, effect sizes, p-values, power analysis and references, and it cross-references citations against Retraction Watch,
Metacheck (formerly Papercheck) Read More »
