One CV's journey through the engine.

Follow a real 19-page faculty CV from its first page to a verified record. The walkthrough below is the one we show partners: first what CVParsa understands about the CV, then what it verifies against the public record.

Watch the walkthrough Read it instead

Jump to

→ next · ← back · F full screen · Open full screen

The slideshow is best on a larger screen. The same walkthrough is written out below, or open the slides in a new tab.

Open the slideshow

The same journey,written out.

Every value here is real: the CV is one of our founders', and the record is the one CVParsa produced from it.

A 19-page CV, as its author wrote it.

CVParsa reads the whole document, whatever its layout. The margin counts are what it extracted from all 19 pages.

Aaron Clauset

Education
Ph.D. Computer Science, University of New Mexico (with distinction)2002 – 2006
B.S. Physics, Haverford College (with honors …)1997 – 2001
2degrees

Academic
Professor, Computer Science Dept., University of Colorado, Boulder2022 – present
External Faculty, Santa Fe Institute2012 – present
Omidyar Fellow, Santa Fe Institute2006 – 2010
⋯
7appointments

Honors
Erdős-Rényi Prize in Network Science, Network Science Society2016
NSF CAREER Award2015
⋯
8honors

Publications
A. Clauset, “How large should whales be?” PLOS ONE 8(1), e53967 (2013).
A. Clauset, “Trends and fluctuations in the severity of interstate wars.” Science Advances 4(2), eaao3580 (2018).
⋯
114publications

Grants
“CAREER: Hierarchical probabilistic models for networks with rich data in scientific domains.” PI
NSF CISE, $550,0002015 – 2020
⋯
22grants

Advising
Postdoctoral Fellows ⋯ Undergraduate Students ⋯
51advisees

Excerpts from the CV, with third-party names left out. The counts on the right are what CVParsa extracted: 2 degrees, 7 appointments, 8 honors, 114 publication entries, 22 grants, and 51 advisees. Everything that follows was derived from this document and the public record.
Each entry is classified the way a search committee would read it.

Titles, degrees, and roles are placed on fixed academic vocabularies, so a field means the same thing in every record.
- Professor, Computer Science Dept., University of Colorado, Boulder, 2022 – presentrolefacultyrankProfessortenure-track
- Omidyar Fellow, Santa Fe Institute, 2006 – 2010rolepostdocA fellowship title, classified as a postdoctoral appointment.
- External Faculty, Santa Fe Institute, 2012 – presentrolefaculty
- Founder and co-CEO, Cevian Labs, Inc., 2025 – presentroleindustry
- Ph.D. Computer Science, University of New Mexico, 2006degreePh.D.research doctorate
- B.S. Physics, Haverford College, 2001degreeB.S.undergraduate
Advisees, by level of supervision (51)

17 doctoral7 postdoctoral11 master's14 undergraduate2 not stated

The CAREER award is recorded twice: once as an honor, once as funding.

The CV lists it in two sections. CVParsa keeps both, each in its own place, so the honor never inflates the funding totals and the grant never inflates the honors.

Listed under Honors

NSF CAREER Award, 2015

Recorded as an honor

Faculty Early Career Development (CAREER) Award

National Science Foundation, 2015

Prestige
prestigious
Scope
national
Field
open to all fields
Career stage
early career
Recognizes
research

Listed under Grants

“CAREER: Hierarchical probabilistic models …” PI, NSF CISE, $550,000

Recorded as funding

NSF research grant

NSF CISE

Type
research grant
Amount
$550,000
Period
2015 to 2020
Role
PI

Each publication is matched to its published record.

On a match, the publisher's record supplies what the CV leaves out: the identifier, full author details, affiliations, and citation counts.

Field	As written on the CV	As recorded by CVParsa
Entry	A. Clauset, “How large should whales be?” PLOS ONE 8(1), e53967 (2013).	How Large Should Whales Be? Journal article, PLoS ONE, 2013
DOI	not given	10.1371/journal.pone.0053967¹
Author	A. Clauset	Aaron Clauset, ORCID iD 0000-0002-3529-8746¹
Affiliation	not given	Santa Fe Institute; University of Colorado Boulder²
Impact	not given	45 citations; field-weighted citation impact 3.9³

¹From the publisher's record of this paper.²At the time of publication, each with a standard institution identifier.³As indexed by OpenAlex.

The CV's 114 entries, sorted

83 journal articles7 proceedings papers4 book chapters16 preprints1 patent, 3 unclassifiable

Across the whole CV: 106 of 114 entries were matched, 99 in Crossref and 7 in other scholarly databases. The record now carries 96 DOIs that the CV never states, and it shows the owner as first author on 25 publications and last author on 38.

Grants are checked against the funder's own award record.

A match canonicalizes the award number, title, amount, and period, and, where the agency publishes it, confirms the person's role.

Field	As written on the CV	As recorded by CVParsa
Award	no award number given	NSF 1452718¹
Title	“CAREER: Hierarchical probabilistic models for networks with rich data in scientific domains.”	CAREER: Hierarchical Probabilistic Models for Networks with Rich Data in Scientific Domains
Amount, period	NSF CISE, $550,000, 2015 – 2020	$550,000, 2015 to 2020
Role	PI	PI²

Award	no award number given	NSF 2022138¹
Title	“NRT: Integrated Data Science (Int dS): Teams for Advancing Bioscience Discovery.”	NRT-HDR: Integrated Data Science (Int dS): Teams for Advancing Bioscience Discovery³
Amount, period	NSF DGE, $3,000,000, 2020 – 2025	$3,000,000, 2020 to 2026⁴
Role	co-PI, with …	co-PI²

¹From the NSF award record; not on the CV.²Named on the NSF award record.³NSF's title for the award.⁴End year per NSF.

Across the whole CV: 22 grants listed. 13 come from funders with public award databases, 10 of those were confirmed in NSF and NIH records, and the CV owner's role was confirmed on 9.

Recognizing a prize and confirming who received it are separate checks.

Whether an award is a recognized distinction, and whether this person received it, are two different questions. CVParsa answers them separately.

Erdős-Rényi Prize in Network Science, Network Science Society, 2016

1Recognized

Matched in the Cevian Labs Academic Honors Registry: more than 9,000 academic honors from over 4,000 conferring organizations.

Erdős-Rényi Prize

Network Science Society

Type: prize
Prestige: prestigious
Scope: international
Field: subfield
Career stage: early career

2Received

Checked separately, against an independent biographical record.

Receipt confirmed

Across this CV, 7 of 8 honors were recognized and 1 receipt was independently confirmed. An unconfirmed receipt is not a negative finding; it means no public record lists it yet.

What the public record confirms for this CV.

Every entry states which authority confirmed it, or that none did. Unconfirmed entries are kept exactly as the CV lists them.

Data class	Listed	Confirmed	Confirmed against	Not confirmed
Publications	114	106	Crossref and other scholarly databases	8, kept as listed
Grants	22	10	NSF and NIH award recordsowner's role confirmed on 9	12, kept as listed
Honors	8	7	Cevian Labs Academic Honors Registryreceipt independently confirmed on 1	1, not in the registry

Example: A. Clauset, “How large should whales be?” PLOS ONE (2013) was matched in Crossref, which supplied its DOI, 10.1371/journal.pone.0053967. The CV gives none.

Why not just askChatGPT or Claude?

Reading a CV is the part general-purpose chatbots already do well. The rest is where the engine earns its keep.

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	114 items listed, 94 counted as publications; 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

Every file 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.

Checked, not judgedVerification is a data-quality check. An unconfirmed entry is reported as exactly that, never as false.

Pick a product.

Four products, one engine, each put to work on a different academic task.

CVParsa for Search Committees

Your whole applicant pool as one spreadsheet: every applicant on the same fields, with publications verified.

Go to CVParsa

CVPaaS

One structured record per CV for academic research, with publications, grants, and honors checked against the public record.

About CVPaaS

COI Pond

A free draft of your NSF Collaborators and Other Affiliations form, built from your CV. Edit it online, then download the spreadsheet for your proposal.

Go to COI Pond

Integrations

The engine inside your own platform, through a secure API, tailored to the data your product needs.

About Integrations