For friends, mentors and writing groups reading a GRFP draft
NSF GRFP Review Rubric for Drafts
NSF's Intellectual Merit factors and Broader Impacts outcomes word for word, with evidence columns, a skim test, a rules check and a comment sheet.
| NSF factor | Evidence found | What's missing |
|---|---|---|
| Plan and conduct research | "I designed a 10-week survey of 40 tide pools" (para. 1) | Who analyzed the data? |
| Work independently | None found | One step taken without being asked |
| Interpret and communicate research | Poster at the campus symposium (para. 3) | What the poster concluded |
| Persist and overcome challenges | "When the first temperature loggers flooded, I rebuilt the housings" (para. 1) | What the rerun showed |
An invented draft. River fills the evidence with quotes, and the ratings stay with the reader.
What you'll get
Score a draft against NSF's exact criteria, with quotes as the evidence
- NSF's nine Intellectual Merit factors and ten Broader Impacts outcomes, verbatim
- Evidence and what's-missing columns, a rating line for each criterion, and a skim test
- A rules check, a one-story check and a sheet for the three biggest fixes
Before and after
A statement in. Evidence with quotes out.
Research plan, first paragraph: "Last summer I designed a 10-week survey of 40 tide pools to test whether heat waves shift snail grazing. When the first temperature loggers flooded, I rebuilt the housings and reran two weeks of sampling."
Plan and conduct research: "I designed a 10-week survey of 40 tide pools" (Research plan, paragraph 1). Missing: who analyzed the data, and what it showed. Persist and overcome challenges: "When the first temperature loggers flooded, I rebuilt the housings" (Research plan, paragraph 1). Missing: what the rerun showed. Work independently: None found. Rating, Intellectual Merit: left for your reader.
Quotes only, never a rewrite. Ratings and fixes stay blank unless you ask River to suggest them.
Why it works
How do you review someone's GRFP draft?
A GRFP review rubric turns NSF's two review criteria into a scoring sheet that a friend, mentor or writing group fills in while reading a draft. This one lists the nine Intellectual Merit factors and ten Broader Impacts outcomes in NSF's own words from NSF 26-526. Each has a column for evidence quoted from the draft and a column for what is missing. NSF says each criterion "is necessary but neither, by itself, is sufficient," so the rubric scores both, separately.
Each criterion gets a rating line on a five-step scale, Excellent to Poor, with one sentence on why. Treat the ratings as a shared language for your group, not a forecast: no rubric predicts a panel. The skim test asks the reader to read only first sentences and bold text, the way a busy reviewer might, then say what they learned. A rules check covers the exact headings, page limits, fonts, margins, references and alt text, and a one-story check tests whether the two statements agree.
Paste a section and River fills the evidence columns with quotes, never rewriting a line, and leaves the ratings and fixes to the reader. For a full read with ratings and ranked fixes, try the mock review. A printed draft cannot show fonts or margins, so check the PDFs themselves with the format checker. To see what strong evidence looks like on the page, compare the draft with these winning GRFP examples.
What lands in your doc
What's inside the GRFP review rubric
- Intellectual Merit, verbatim
NSF's nine factors, each with evidence found and what's missing, plus a check of the research plan itself. - Broader Impacts, verbatim
NSF's ten outcomes the same way, with a check that past work and future plans are specific. - A rating line for each criterion
Excellent, Very Good, Good, Fair or Poor, with one sentence on why. - The skim test
First sentences and bold text only, then what the reader learned and what they missed. - Rules, one-story and clarity checks
Exact headings, page limits, fonts, margins, references, alt text, eligibility, whether both statements agree, and jargon. - A comment sheet
A rating summary, what's working, and the three most important fixes, in order.
How it works
From a draft to three clear fixes
Open the rubric
Click Edit with AI for your own copy in River, or download it as a Word file to print.
Paste a section
Optional. River fills the evidence columns with quotes from it and lists the first sentences for the skim test.
Read and rate
The reader works through the draft, checks the evidence, and rates each criterion.
Hand back three fixes
Write the three most important fixes, each naming the statement, the paragraph and the change.
Questions GRFP applicants ask
Common questions
What rubric do GRFP reviewers use?
NSF reviews every application on two criteria, Intellectual Merit and Broader Impacts, and the solicitation lists factors reviewers may consider under each. This rubric uses those lists word for word. Its rating lines use a five-step scale, Excellent to Poor, as a shared language for your readers. They are not NSF's form and do not predict a panel's rating.
What are the Intellectual Merit criteria for the GRFP?
NSF defines Intellectual Merit as "the potential to advance knowledge." Reviewers may consider your ability to plan and conduct research, work independently and in a team, interpret and communicate research, take initiative, think creatively, solve problems, and persist through challenges. They also weigh your demonstrated intellectual ability, shown by grades, coursework and awards.
What counts as Broader Impacts for the GRFP?
Your potential to benefit society. NSF's list of outcomes runs from increasing participation in STEM and improving STEM education through outreach and mentoring to public engagement, collaboration with industry, well-being, national security, economic competitiveness and research infrastructure. No one needs all ten. A strong section shows past activities with your own role, and future plans that grow out of them.
Who should use this rubric?
Anyone reading a GRFP draft for someone else: a labmate, a mentor, a writing center tutor or a writing group trading statements. A reader from a neighboring field is useful, because they trip on the jargon a reviewer outside your exact topic would. Fill one copy for each application, and quote the draft instead of paraphrasing it.
How is this different from River's mock review?
The rubric is for a human reader, and the ratings and fixes are theirs to write. The mock review is River's own read: it rates both criteria, runs the skim test and ranks five fixes across both statements. Using both gives you two independent reads before you submit.
Can River fill in the ratings?
Only if you ask. When you paste a statement, River fills the evidence columns with quotes and lists the first sentences for the skim test, then leaves the ratings and fixes blank. Ask, and it suggests a rating for each criterion, labeled as its estimate, with one sentence on why. It never rewrites the statement.
Your next step
More for your GRFP application
Give feedback a GRFP reviewer would recognize
Open the rubric with NSF's criteria in place, or paste a statement and River fills the evidence with quotes, leaving the scoring to you.