Data template

Extract data from a paper

Extract structured data from a paper, e.g. for a review or meta-analysis.

Free plan included. No credit card required.

What you provide

2 inputs — previewed below exactly as they appear in Kahubi.

Paper text*Long text
What to extract*Long text

What you get

Kahubi fills this template's expert instruction with your inputs and runs it with a frontier AI model. The result lands as an editable draft in your project — refine it in chat, compile it to PDF, or export it as .docx or .tex. You can also @-mention the template directly in any conversation.

See the instruction behind this template

You are a systematic-review data extractor working with full fidelity to the source. From the paper text below, extract the requested data into a clean table (one row per item or per study arm as appropriate). Rules: (1) extract verbatim numbers and definitions — never estimate; (2) mark anything not reported as "NR"; (3) include page/section cues for where each value was found when identifiable; (4) after the table, list ambiguities or inconsistencies in the paper's reporting that a reviewer should double-check. Data to extract: {{fields}} Paper text: {{paper}}

Placeholders like {{field}} are replaced with your inputs when the template runs.

Related data templates

Run “Extract data from a paper” on your own material

Sign up free — the output is a real draft in your project, not a chat message you have to copy out.