You describe your research once. The most relevant new papers arrive in your inbox with a note explaining why each one matters. Here’s what happens in between.
Each stage narrows the field with increasing precision.
Thousands of new papers
Across all disciplines
Six queries, four databases
Tailored to your profile
0 candidates
Merged and deduplicated
Scored to your profile
Every candidate ranked
Scientific evaluation
Four-dimension rubric
Your digest
Each paper explained
You describe your research once: the question you’re asking, the methods you use, the constraints you face. From that description, we build a structured profile of your work and what matters to you.
That profile generates search queries across six categories, from your core domain to adjacent fields that might hold a technique or insight you haven’t seen yet. Each query is shaped for the database it targets.
Your Research
“Investigating LRRK2 kinase inhibition as a therapeutic target for Parkinson’s disease using iPSC-derived dopaminergic neurons and mitochondrial functional assays...”
Generated Queries
Your queries run against four independent academic databases simultaneously. Each covers different corners of the literature. Together, they catch what any single source would miss.
Allen Institute’s citation graph. 200M+ papers with full citation context and metadata.
200M+ papers
The broadest open academic index. Covers non-English journals, emerging fields, and interdisciplinary work.
250M+ works
Preprints indexed hours after submission. Physics, CS, math, and biology before journal publication.
2.4M+ preprints
NCBI’s gold standard for biomedical literature. Activated automatically for life science projects.
36M+ articles
Merge & Deduplicate
Results are deduplicated across all four sources. Papers found by multiple databases get a stronger signal.
Search engines rank papers by their own algorithms. Useful, but generic. A cross-encoder reads your full research description alongside each paper’s abstract in a single pass, scoring how precisely the two relate. Papers are collected across a rolling two-week window to account for indexing delays. Every candidate gets scored. The top papers advance to final evaluation.
Traditional Search
12 results from one database
Our Approach
Found across 4 databases
Relevance alone isn’t enough. A paper can be on your topic but incremental, or use interesting methods but lack evidence.
A language model reads each finalist alongside your interest profile and evaluates it on four dimensions that reflect how researchers actually assess papers. Review articles are detected and filtered based on your preferences. The highest-scoring papers are selected for your digest.
For each paper you receive, the model writes a two-sentence note explaining exactly why it matters to your work. Not a generic summary, but a targeted explanation connecting the paper’s findings to your hypotheses, methods, or goals.
Scientific Rubric
LRRK2 Inhibition Restores Mitochondrial Function in iPSC-Derived Parkinson Neurons
Cell Stem Cell · Feb 2026
Relevance Note
Why this matters to you
“Demonstrated that LRRK2 kinase inhibition rescues mitochondrial membrane potential and complex I activity in iPSC-derived neurons. The dose-response data and mitochondrial assay approach directly inform the researcher’s experimental design.”