Faculty rank
- Regents Professor of ChemistryDistinguished Professortenure-track
- Smith Family Endowed ChairProfessortenure-track
- Research Assistant Professornon-tenure-track
Research‑ready data from academic CVs.
CVPaaSfor academic research
One structured, machine-readable record per CV, with publications, grants, and honors checked against the public record.
An excerpt of a real CVPaaS record, pseudonymised: names, institutions and some details changed.
$2 per CVat every tier
One JSON recordper CV, ready for analysis
Four tierstake only the data your project needs
A whole scholarly career,in one record.
CVPaaS reads an academic CV, whatever its layout, discipline, country, or length, and returns a structured record of that person's scholarly career.
- Person and standingCurrent institution, academic unit, and position; year of doctorate and of first faculty appointment
- Education and trainingDegrees, fields, institutions, years, and postdoctoral training
- EmploymentEvery appointment, across academia, government, industry, clinical practice, and research staff roles
- AdvisingThe person's own advisors, and the advisees they supervised: level, dates, thesis titles
- PublicationsThe full bibliographic record, with complete author lists, venues, identifiers, and citation metrics
- Research fundingAwarded grants, contracts, and fellowships: funder, award number, amount, period, and role
- HonorsPrizes, medals, honorific fellowships, society memberships, named lectureships, and competitive recognitions
- Research interestsScholarly keywords and a short characterization of the research program
- Institutional identityEvery institution on the CV, resolved to a canonical name, a standardized location, and a persistent identifier
It understands academia.
CVPaaS doesn't simply lift strings off the page. It classifies every entry onto closed academic vocabularies, so a field means the same thing in every record.
- Ready for programmatic analysisClassification fields are closed vocabularies, so you can filter, count, and aggregate them directly, with no hand-coding.
- Comparable across institutions and fieldsPeople at different institutions, in different disciplines and countries, are described on the same terms.
- Built for the scale of careersAssemble consistent records for hundreds or thousands of academics, for large-scale studies of academic careers.
A few examples of what it standardizes and classifies.
Degrees
- PhDPHDDoctor of PhilosophyPh.D.research doctorate
- BA (Hons)B.A.undergraduate, with honors
- MBAM.B.A.professional master's
Advising
- Dissertation co-chairPh.D. advisorDoctoral advisor
- Honors thesis advisorUndergraduate advisor
- Ph.D. and M.S. advisorTwo recordsdoctoralmaster's
Career roles
- Chair, Department of HistoryAdministrative
- Postdoctoral Research AssociatePostdoc
- Senior Research ScientistResearch staff
Publications
- Proceedings of the Annual Conference on …Conference paper
- arXiv preprint, 2023Preprint
- Journal of …, 12(3):45–67Journal article
Funding or honor?
- Outstanding Teaching AwardHonornot funding
- NIH K99/R00 Pathway to Independence AwardGrantcareer-development fellowship
- NSF research grant, $450,000Grantresearch grant
Grants
- Principal Investigator, NSF, $450,000Research grantPI
- Sloan Research FellowshipFellowshipindividual
- NIH T32 training program (Director)Training grantinstitutional
An authoritative recordof each career.
CVPaaS validates what a CV lists against the public record: publications against Crossref and other bibliographic databases, grants against funders' award records, and honors against the Cevian Labs Academic Honors Registry. The result is an authoritative view of each person's academic career.
Starting from the CV sidesteps author disambiguation.
Searching by name
- Picks up other researchers with similar names
- Misses spelling variants, name changes, and earlier career stages
Starting from the CV
- Begins with the person's own record of their work
- Confirms each entry against the source that published, funded, or awarded it
Every record carries its own provenance: which authority confirmed it, or that none did. So you can measure how much of any CV an independent source corroborates. Checks are tuned for precision, and an unconfirmed record is reported as exactly that, not as a missing achievement.
Where each record is checked
- Publications
- Crossref and other authoritative bibliographic and library databases. On a match, the published record replaces the CV's version
- Grants
- NSF, NIH, USASpending, UKRI, and the EU's CORDIS. A match confirms the award number, title, amount, and period and, where the agency publishes it, the person's role
- Honors
- The Cevian Labs Academic Honors Registry (more than 9,000 honors from more than 4,000 organizations), then, separately, an authoritative biographical source to confirm that this person received that award
Four tiers, one price.
Every tier costs the same. The difference is time: each tier reads and checks more of every CV, so higher tiers take longer. How much longer depends on the CVs themselves, especially how long their publication and grant lists are. Choose the tier your analysis needs.
Basic
Supports analyses of education, employment, and mentoring.
Processing timeQuickest
- Person, interests, education, employment, and advising
- Publications
- Grants
- Honors
Plus
Supports analyses of scholarly productivity across institutions.
Processing timeLonger, depending on the length of each publication list
- Person, interests, education, employment, and advising
- Publications
- Grants
- Honors
Premium
Supports analyses of funding’s impact on scholarship.
Processing timeLonger still, as grant lists are checked too
- Person, interests, education, employment, and advising
- Publications
- Grants
- Honors
Complete
Supports analyses of career merit and achievement.
Processing timeLongest, with honors checked as well
- Person, interests, education, employment, and advising
- Publications
- Grants
- Honors
$2 per CV, at every tier. CVPaaS is available for academic research projects only.
Getting access.
Request a code
Tell us about your research project. Access is by authorization code, for academic research only.
Upload your CVs
One ZIP file of CVs or dossiers, with your tier and your code.
Download the records
A ZIP of JSON files, one structured record per CV, ready for downstream analysis.
See it work on a real CV
One CV's journeyFrom its first page to the finished, verified record. Plays automatically.
Click the slides or use the arrow keys to step through at your own pace. Open full screen · Full walkthrough
Why not just ask ChatGPT or Claude?Reading a CV is the part general-purpose chatbots already do well.
| Task | General-purpose chatbot (ChatGPT, Claude) | CVParsa |
|---|---|---|
| Read one CV and summarize it | Does this well | Does this well |
| Apply the same fields and vocabulary to every CV in a pool of hundreds | Output varies between runs | One schema, fixed academic vocabularies |
| Know that a fellowship title can be a postdoc, and that a CAREER award is both an honor and a grant | Inconsistently | Applied the same way to every CV |
| Count publications | Depends on how the question is asked | Publications counted by type; preprints and patents kept separate |
| Confirm each record against Crossref, NSF, NIH, and Cevian Labs databases | Not systematically, and prone to inventing citations it cannot find | Every record states which authority confirmed it, or that none did |
| Handle confidential applicant files | Consumer accounts raise data-governance questions | Encrypted, never used to train AI models, originals deleted within 30 days |
Your research data stays private.
EncryptedAES-256 at rest, TLS in transit.
Never used for trainingSubmitted files are never used to train third-party AI models.
Deleted within 30 daysOriginal files are kept at most 30 days, for customer support only.
Only what you chooseEach tier extracts only its data classes, so a project collects no more than it needs.
Questions.
What do I get back?
A ZIP of JSON files, one structured record per CV, ready for downstream analysis. Classification fields use closed vocabularies, so they can be filtered and aggregated directly, and institutions and publications carry persistent public identifiers, so records join cleanly to other bibliometric and institutional data.
Who can use CVPaaS?
CVPaaS is available for academic research projects only. For hiring and search-committee use, see CVParsa for Search Committees; to build CVParsa into a platform, see CVParsa Integrations.
How do I get an authorization code?
Email contact@cevianlabs.io to discuss your research project. Each code authorizes a set number of CVs.
Which tier should I choose?
Choose by the data your analysis needs. Basic covers the career record and is the quickest; Plus adds checked publications; Premium adds checked grants; Complete adds recognized honors. Each tier reads and checks more of every CV, so higher tiers take longer. The price is the same at every tier.
How long does a job take?
It depends on the tier, the number of CVs, and what is on them. Larger batches take longer, especially when they contain thousands of publications to verify; long grant lists and slow responses from the external databases add time too. We email you as soon as your results are ready.
How much does it cost?
$2 per CV processed, at every tier.
What files can I submit?
PDFs only: one PDF per person (a CV or a full dossier), all in a single ZIP file of up to 200 MB. CVPaaS can't split one PDF that contains several CVs.
Which languages and academic fields does CVPaaS support?
CVPaaS understands CVs in most major languages and recognizes international institutions and venues. Results are always returned in English.
All academic fields are supported. CVs in fields without standard publication formats (for example, artistic performances) may return partial publication data.
How accurate is CVPaaS?
Academic CVs vary widely in format across fields, and CVPaaS is built to handle that variation. No automated tool is perfect.
Every checked record states which authority confirmed it, or that none did, so you can see exactly which entries an independent source corroborates.
How does CVPaaS handle confidential information?
Files are encrypted with AES-256 at rest and TLS in transit, and are never used to train AI models. Original files are kept at most 30 days, for customer support only.