About Evidence Hub
Evidence Hub puts one search bar in front of the places published research lives, then does the reading-order work for you: it merges duplicates, ranks by how well each study matches your question, and adds a summary and a data sheet to every result. Students use it as a website for research, and researchers and clinicians use it to search for studies online before a systematic review or meta-analysis.
How it works
- Search once. Put your topic or question in one search bar. You don't pick a database first.
- Read the ranked results. Results are sorted by how well they match, with an AI summary on every card and the weakest matches folded away. Filter by field, publication type, approach and study design, and for medicine by evidence level.
- Dig in or move on. Open a study for its data sheet, chat with the paper, or save it and keep searching.
Where the data comes from
Every search queries PubMed, Europe PMC, Semantic Scholar, ClinicalTrials.gov, OpenAlex and arXiv. Open-access full texts, so you can search for studies as PDF for free, are found through the publishers' own open copies and Unpaywall. For paywalled papers you can upload your own copy; it is checked and stays private to you.
Free, with points for AI
Searching, saving and export are free. AI work is paid for in points; new accounts start with a balance and a verified PDF upload earns more.
What the AI does, and does not do
Summaries and answers are grounded only in a study's own abstract and, when available, its verified full text. The model is told to say when the material doesn't answer a question rather than guess, and every summary is labelled with the provider that wrote it. Study type, subjects, sample size and evidence level are inferred automatically and can be wrong.
Evidence Hub is not medical advice. Always check the original paper.
Privacy
Your saved studies, folders and chat history are private to your account. See the Privacy Policy and the Terms of Service for details.