JevMade

Sign in
← Back to experiments

Benchmarks & research

Jev Abstract Screener

A paper-screening experiment ranks research abstracts with Jev, then checks how many relevant studies a shorter reading list would miss.

Bookmark: Jev Abstract Screener Keep this in your collection.
Leave a noteWhat would you try with this? : Jev Abstract Screener

Only you can see your notes.

Source screenshot of Jev Abstract Screener
SOURCE SCREENSHOTFull screenshot ↗

What it does

The author missed the target: finding 95% of included studies took reading 62% of the list. The rules were written with knowledge of this dataset, not tested on an unseen review.

How you can use it

You can borrow this study’s way of testing a shorter reading list. Start with papers that researchers have already judged. Ask Jev, an AI service, to put likely matches first. Compare its order with a simple word search.

Then count how many wanted papers each list misses as you read down it. That shows the cost of reading fewer papers. This study cannot tell you when it is safe to stop reading a new list.

Your note

Only you can see this. Clear the text and save to remove it.

Keep what you save

Sign in to keep bookmarks and private notes on every device. We email you a link; there is no password, and the same link creates your account.