Skip to content

See clearly when AI
makes it easy to
stop looking.

20/20 gives you the context behind every claim before you read a line, and leaves the judgment yours.

Request Demo See how it works
Submission
20/20 Notes
Reviewer Notes
Nanoparticle-mediated drug delivery in glioblastoma
Submitted to International Review of Biomedical Systems, 2026
Recent studies demonstrate that nanoparticle carriers achieve 94% blood-brain barrier penetration rates in vivo, representing a significant advance. Solvenn et al. (2026) established the definitive therapeutic window for temozolomide encapsulation, corroborated by six independent analyses. Furthermore, no published study has reported adverse hippocampal accumulation at doses below 5mg/kg.
20/20 Analysis
Ghost Citation Detected
Solvenn et al. (2026) does not resolve in any bibliographic index. Authors and DOI do not exist.
FABRICATED REFERENCE
Unsupported Quantitative Claim
The 94% penetration rate is not supported by any cited source. The highest published rate in the retrieved literature is 41% (Vosseler et al., 2026).
CONTRADICTED BY LITERATURE
Omission Bias Detected
Ramé et al. (2026) reports hippocampal accumulation at 3mg/kg. The claim conceals contradicting published evidence.
SELECTIVE OMISSION
Citation Check
Claim Extract
Retrieval
NLI Verify
Notes

Credibility now outruns verification.

Producing convincing information has never been easier. Verifying it accurately hasn't scaled.

20/20 turns reviewers into domain experts by performing the due diligence on every claim, so they can move through high-stakes, evidence-based review faster, with better quality.

Industries

Reads alongside you. Decides nothing.

20/20 checks every claim and citation as you read, and puts the evidence beside the page. The call stays yours.

  • Citation authenticity
    Every reference checked against live indexes and retraction records.
  • Claim-level verification
    Each claim checked against the source it cites.
  • Open-literature grounding
    Surfaces related and prior work beyond the citations, including what the author left out, and shows where each contribution sits against it.
  • Works alongside you
    Notes appear beside the document as you read, never as a verdict.
  • Workflow integration
    Fits into the review systems your team already uses.
Not an LLM. It calculates against the record, so the same input gives the same output.

20/20 vs. general-purpose AI

Built for reviews where every claim needs a source.

Focus
20/20
General-purpose AI tools
How claims are checked
20/20Each claim tested against the source it cites
General-purpose AIA generated opinion on whether the document seems right
Citations
20/20Every reference checked against live indexes and retraction records
General-purpose AICan miss fabricated references, and can invent new ones
Consistency
20/20Same input, same output, every time
General-purpose AIAnswers can change from one run to the next
Evidence
20/20Every flag shows the source passage behind it
General-purpose AIConclusions often come without a traceable source
The reviewer's role
20/20You assess first, then see the flags. The decision stays yours.
General-purpose AIOffers a verdict that is easy to accept without reading

Watch 20/20 process a submission.

A live walkthrough on a document from your field.

Book a demo

Join our pilot.

Field Notes

Feature
The research you have never read is already shaping your life
The drug your doctor prescribed, the bridge your city approved, the model your employer uses. Each one was built on a chain of published research.
Kinjal · June 2026
Technical
Why claim-level NLI beats document-level detection
Checking whether a whole paper seems fine misses the problem entirely. The fabrication is almost always in a single sentence.
Kinjal · May 2026
Integrity
We are about to train AI on a literature it helped corrupt
Models get trained on published research. That research is increasingly written by models. The claims in it are not being verified.
20/20 Team · April 2026
Read the journal

Research integrity
in the age of AI.

Insights on the replication crisis, AI-generated research, and what happens when the record breaks down.

Feature
The research you have never read is already shaping your life
The drug your doctor prescribed, the bridge your city approved, the AI model your employer uses. Each one was built on a chain of published research. Most people never see that chain. But when it breaks, everyone feels it.
KinjalJune 20267 min read
Read
02
Technical
Why claim-level NLI outperforms document-level detection for scientific integrity
Checking whether a whole paper seems fine misses the problem entirely. The fabrication is almost always in a single sentence.
KinjalMay 20266 min
Read
03
Opinion
Science has always optimized for publication. AI just handed that problem a power tool.
The integrity crisis did not start with generative AI. It started with publish or perish and a system that rewards output over correctness.
KinjalMay 20266 min
Read
04
Integrity
We are about to train AI on a literature it helped corrupt. Nobody is talking about what comes next.
Models get trained on published research. That research is increasingly written by models. The claims in it are not being verified.
20/20 TeamApril 20267 min
Read
More
coming soon.
New pieces publish regularly. Check back soon.