Pre-submission integrity review
A pre-submission integrity review for high-stakes scientific manuscripts. It reads your whole paper the way a careful reviewer would, and verifies every claim and citation at its primary source. A person re-derives the load-bearing findings and releases it by hand. We flag. You decide.
Author-side · Before submission · Confidential by written agreement
“I could check it 500 times and I’m still going to miss something. At some point you become blind to it.”
A page from the sample review, invented to show the form. Read it in full →
Act I · The problem
From the outside, you cannot tell whether a manuscript’s references are solid or invented. It is not hypothetical, and the cost is real. The two figures below each open to their primary source.
1 in 277
Published biomedical papers found to contain fabricated references in early 2026, in an audit of 2.5 million papers.
Topaz et al., “Fabricated citations: an audit across 2.5 million biomedical papers.” A 2026 research letter in The Lancet, reporting a single audit. PMID 42107362. These were papers that had already passed peer review. Check the record at PubMed.
$392,582
Mean direct-funding cost of a single misconduct retraction, among NIH-funded papers.
Stern et al., “Financial costs and personal consequences of research misconduct resulting in retracted publications.” eLife, 2014. PMID 25124673. Scope: NIH-funded papers, 1992 to 2012, misconduct retractions specifically. Check the record at PubMed.
Every figure on this page expands to the primary record it comes from. If a number here does not match its source, tell us. That is exactly the kind of error this service exists to catch. The full analysis, with every source, is here: Six Times the Rate.
A note from Ryan Gruzen
Science builds on trust in a single citation: your work on someone else’s, theirs on the next, all the way down. When one is quietly wrong, everything above it inherits the mistake, and no one downstream can see it. ASI exists to close that gap, between what a paper claims and what its sources actually support. Source review is where I start, at the smallest piece I can check.
Act II · The review
It tells you what a careful reviewer would raise, and the repair available for each. It never rewrites your prose or your argument. Three commitments hold everywhere:
Verified at the source
Every reference read at its origin, field by field. Not “we ran it through AI.”
Every decision yours
Corrections are proposed, never imposed. You decide every change.
A person releases it
A person reads the full record and releases it by hand. No automated send.
More than the citations. The whole manuscript, read with the same discipline.
A review covers your manuscript across the dimensions it needs, in the order that serves it, not a fixed checklist. For one paper that means the message first; for another, the citations. One standard holds throughout: verified at the source, and nothing decided for you.
Every reference resolved at its primary source (PubMed, Crossref), including those inside tables and figures: does the work exist, is the identifier the right one, are the authors, journal, and year correct.
Not just whether a source exists, but whether it says what your sentence claims, at the same scope and population. A real, correctly cited paper can still be the wrong support.
A structural read of every exhibit: the right figure in the right place, exhibit counts that match the text, and captions that claim no more than the figure shows.
The throughline of the argument, the title and abstract (alternatives offered, never imposed), and a check for passages that read as AI-drafted rather than yours.
Formatting and renumbering in your journal’s required style, prepared as tracked changes you accept or reject. The one place a review touches the file.
Word and reference limits, reference style, and structural requirements, checked against the journal’s own guidelines the day of the review.
Every load-bearing finding re-derived by a pass that does not share the first one’s inputs, then released by a person. The tool that finds never checks.
Seven dimensions, one review. Every load-bearing finding verified independently, then released by a person.
1
Entrust your manuscript
A confidentiality agreement first, then your near-final draft and target journal.
2
We read it at the source
Every point checked at its origin, citations at their registry, never by title alone.
3
You receive a decision record
The discrepancies, the repairs, and the one or two calls that matter, elevated.
4
A person releases it
Read in full and released by hand. The software cannot send on its own.
What it is not
Not a rewrite. Your prose and your argument stay untouched. Reference formatting comes as tracked changes you accept or reject.
Not a verdict. The readiness read is a prediction, labeled as one. Never a score, never a guarantee.
Not publisher-side screening. No paper-mill detection, no image forensics, no plagiarism scan. Different tools, a different desk.
Not a judge of your science. Merit, ethics, and intent stay with you.
We read your manuscript the way a reviewer would, and check it against its primary sources. We don’t judge the science’s merit. That’s yours.
What you receive
Four artifacts. Two are held until a person releases them; two finalize as your decisions land.
The email body that accompanies your review.
Held until releaseThe structured decision document, and the full verification record.
Held until releaseYour full reference list, set to journal style.
Finalizes with decisionsWhich citation sits at which sentence, and its number.
Finalizes with decisionsBefore anything else
Before you send anything, we sign a confidentiality agreement scoped to your manuscript. Your work is read only to complete your review, never used to train any model, never shared, never reused.
The engagement itself stays confidential: no public attribution, no “powered by.” Particular retention terms go in writing.
Act III · The method, shown
Excerpts in the exact shape of a real review, invented to show the form; no client manuscript appears anywhere on this page. Or read a complete sample review, start to finish: the verdict, every finding, the full reference record, and the review’s own errata. Every detail is invented.
The errata · The review corrects its own work, in the open
“A self-check caught one place this review claimed more than it had verified: an earlier draft said a wrong identifier ‘points to a different paper.’ Corrected: the review confirmed only that the listed identifier is not the correct one for the cited work; it did not verify where the wrong identifier leads, and does not claim to.”
Before release, every review checks itself and discloses any place an earlier draft over-stated. A review that publishes its own corrections is the one you can trust. We would rather show a catch than claim we never need one.
Findings · Each one traceable, each with a repair
Substantive
“The abstract hedges responsibly; the conclusion drops the hedge and asserts causation. Repair: harmonize the language to the hedged register the limitations section already commits to.”
Findings arrive in tiers, each with the same structure: the claim as written, what the source actually is, why it matters, and the repair available now. No new research required.
A pattern we see
A pattern common enough to name. An author runs a near-final manuscript through a leading AI assistant, and it comes back with a verdict:
The assistant’s verdict
“Fully submission-ready. A clean bill of health.”
What a source-level review finds
A source that does not support the claim it is cited for.
An author listed on a reference who had not contributed.
Identifiers that resolve to the wrong work, or to nothing.
An abstract in the wrong format for the target journal.
The assistant graded the prose. It could not check whether the sources were real. That check happens at the registries where the sources live, one reference at a time, and it is the check this review is built on.
“I found the feedback especially helpful and constructive.”
Unattributed by design. Engagements are confidential, and no client is named here without written consent. Attributed words will appear when, and only when, a client chooses to be named.
We don’t ask you to trust this review. We ask you to check it.
Before you need us
A short pre-submission citation checklist: the questions we ask of every reference list, in a form you can run against your own manuscript. Free, yours whether or not we work together, and it makes your submission stronger on its own.
Open the checklistKnow a colleague with a submission coming up? The checklist is easy to pass along, and it asks nothing of your name.
More free tools, same spirit: the claim-support self-audit, the retraction-risk reckoner, and a printable grant-deadline pass.
The questions worth asking
Still holding questions? Good. These are the ones authors actually ask, answered plainly.
Yes, by written agreement signed before anything is sent: scoped to your manuscript, no secondary use, no training, no attribution.
A general AI assistant cannot catch its own fabricated citations. This is built on the opposite principle: the tool that produces a finding never checks it, every citation is resolved at its registry, and a person confirms every load-bearing conclusion before it goes out.
Journal screens are automated, at-scale, and run after you submit (text overlap, AI-text detection). This is the opposite end of the desk: author-side, before submission, human-released, and aimed at what those screens skip: whether each citation is real and supports its claim, and whether the rest of the manuscript holds up the way a careful reviewer would read it.
One manuscript, read across every dimension above: citations verified at their source, claim-to-source fit, figures and tables, message and audience fit, reference mechanics in the style your journal requires, and submission compliance, each finding with the repair available and an independent check behind it. Includes the initial review plus one re-review of your revision; further rounds are priced the same way. Corrections are proposed as tracked changes you accept or reject, never silent edits.
You are the author, and nothing is changed in your manuscript unless you accept it. If you believe a finding is wrong, say so: it is re-checked against the same primary source and either corrected or explained. The review's own errata practice applies to itself first.
No. It is a review, not a rewrite: it leaves your prose and your argument to you. It tells you what a careful reviewer would raise; you make every change.
A named engagement, not a queue. Timelines are set against your actual deadline when you request the review, and we tell you honestly what we can commit to.
Per manuscript, set in conversation and sized to the manuscript and its deadline. This is a professional, human-released engagement, not an automated scan, priced in the neighborhood of what it costs to publish the paper itself. Weigh it against the cost of getting a submission wrong: a rejection cycle in months, or a retraction whose mean direct cost, in the one careful audit we know of, ran to hundreds of thousands of dollars. A pre-submission source check is inexpensive insurance.
A person is accountable for every review and releases it by hand. Software verifies at the source registries; the person reads the full record and confirms each load-bearing conclusion before anything is sent. We would rather show the method than a bio: every review documents how its checks were run, so you can re-run them.
It is real, and it is early. Our first engagements are with senior academic authors, and they are confidential, so you will not find a wall of endorsements here. What we can show is the method, including how it corrects its own work. We put the method first for a reason: a testimonial asks you to trust someone else's judgment; the method invites you to use your own.
The invitation
One manuscript is the base unit: the full review, plus one re-review of your revision. If you have a high-stakes submission ahead, send word. The confidentiality agreement comes first, the manuscript after. What you get back is a record you can check yourself, line by line.
Request a review