Using AI—particularly Anthropic’s Claude—and a development process described as “vibe coding,” Adam Hyde built two scholarly publishing platforms: EasyJournal (a more conventional system) and Kotahi (a collaborative-first alternative). EasyJournal mirrors legacy platforms like OJS and Janeway, while Kotahi…
A collaborative system to benchmark and compare Retrieval-Augmented Generation (RAG) architectures using real-world publisher content. Silverchair and OpenSource Connections co-designed a robust evaluation pipeline—using Python, LlamaIndex, RAGAS, and LangSmith—to generate question-context-answer triplets, run RAG models, and score outputs…
RAG Evaluation Framework Read More »
ReviewBench is an open-source, venue-agnostic framework comparing human and AI reviews across structure, alignment with a paper’s major claims, impact, and critique category — benchmarking infrastructure for the AI peer review wave.Notes & quotesPreprint: https://www.biorxiv.org/content/10.64898/2026.04.17.719279v1.full
The Silverchair AI Lab is an interactive, user-friendly platform designed for publishers to experiment with various AI models, applications, and use cases. It serves as a space to deepen understanding of AI technologies and refine AI strategies within…
Silverchair AI Lab Read More »
