F-001
Figure similarity candidate
Figure 3 panels B and D require author review.
Research Integrity QC AI
AI-assisted pre-submission quality control for manuscripts, figures, statistics, and source data.
A confidential workflow that helps research teams flag potential issues for human review before journal submission.
Early pilots use synthetic, public, already-submitted, de-identified, or otherwise non-sensitive materials only.
Findings
12
High
1
Moderate
4
S-001
Statistical reporting mismatch
Methods describe SD; figure legend describes SEM.
D-001
Source-data alignment
Manuscript states n=8; source CSV shows n=7.
Downloadable QC report
Evidence-linked findings, calm severity labels, and recommended author actions.
A confidential QC workflow before submission
The first product should be narrow, useful, and trusted: upload non-sensitive files, run structured checks, review evidence, then generate a practical report.
Prepare package
Manuscript, figures, tables, and optional structured data.
Run QC checks
Manuscript consistency, figure review, statistics, and data alignment.
Review findings
Evidence locations, confidence levels, and calm recommendations.
Correct before submission
Use the report as a pre-submission checklist for the research team.
Built around concrete report value
The sample package includes seeded issues so potential design partners can evaluate the report format without sharing unpublished or sensitive data.
- Manuscript claim drift and missing verification statements.
- Figure panel similarity candidates for human review.
- SD/SEM and sample-size consistency checks.
- Downloadable report template for concierge alpha pilots.
Request pilot access
Use this early form to start a discovery conversation. Do not send confidential manuscripts, identifiable patient data, or unpublished source datasets through this page.
Positioned as quality improvement, not accusation
This workflow flags potential issues for human review. It does not determine misconduct, fabrication, falsification, image manipulation, plagiarism, or fraud.
Contact Xi-Long Zheng