Cevian Labs — CVParsa

Faculty CV
Analysis.
Automated.

Upload a ZIP of academic CVs or dossiers. CVParsa extracts and structures the data your search committee needs — person, education, employment, publications — into a single, clean spreadsheet.

Start Processing → View Pricing

applicant_pool.csv — CVParsa Plus Output 127 rows · 18 columns

Name	Position	PhD Inst.	PhD Year	Pubs	1st Auth.
Adams, J.	Asst. Professor	MIT	2017	47	18
Chen, L.	Assoc. Professor	Stanford	2013	83	31
Williams, R.	Professor	Harvard	2009	142	57
Okonkwo, A.	Asst. Professor	U. Michigan	2019	29	14
Patel, S.	Lecturer	Cambridge	2015	61	22
⋮	⋮	⋮	⋮	⋮	⋮

127 applicants processed · Plus tier View real NAS sample →

Fields shown: a subset of the 18 available in Plus tier.

~5 min

per 100 files

~99%

accuracy rate

All

academic fields

What CVParsa Extracts

Fields available across tiers. Plus tier required for publication data.

Field Group Extracted Data

Person Name, gender (inferred), email, current position, institution, department

Interests Research keywords and narrative interest summary

Education Highest degree, PhD institution, PhD advisor, field, and year

Employment Current and prior positions, institutions, and appointment types

Publications Plus+ Total count, 1st-author, last-author, venue-specific counts. Crossref-verified.

Pool Visual Premium Infographic summary of aggregate applicant pool composition

Technical Specifications

Input requirements, processing characteristics, and security properties.

Property Value

Input format PDF only (individual CV or full dossier). One file per applicant. Delivered as ZIP archive.

Throughput ~5 minutes per 100 files. No per-batch limit.

Languages Input: all major languages. Output: English.

Accuracy ~99% across all fields in testing across hundreds of CVs in all disciplines.

Encryption AES-256 at rest. TLS in transit.

AI training Submitted files are never used to train third-party AI models.

Retention Input files retained for maximum of 30 days for customer support only.

How It Works

Five steps from ZIP archive to structured spreadsheet. View a real sample output →

ZIP your files

One PDF per applicant. CVs or full dossiers.

Upload to CVParsa

Select tier and output options.

CVParsa processes

~5 min per 100 files. Secure server.

Configure output

Choose fields. Omit signals.

Download & evaluate

One spreadsheet. All applicants.

Steps 1–2: Prepare and upload your files

Step 3: Secure, automated extraction

Steps 4–5: Download and evaluate

Pricing

Flexible Processing Tiers

Per CV document processed. Multi-use licenses available.

	Basic $3/file	Most Popular Plus $5/file	Premium $7/file
Person, Interests & Education	Included	Included	Included
Employment information	Included	Included	Included
Publication extraction & metadata	Not included	Included	Included
1st & last-author pub counts	Not included	Included	Included
Venue-specific publication counts	Not included	Included	Included
Infographic applicant pool summary	Not included	Not included	Included
All tiers: AES-256 encryption, field omission, PDF-only input.	Select Basic	Select Plus	Select Premium

Ready to save your committee time?

Upload your ZIP of CVs and get a consolidated spreadsheet back today.

Process My CVs →

Frequently Asked Questions

What is the output of the process?

CVParsa produces a spreadsheet — one row per input PDF — detailing extracted characteristics of each applicant.

Basic: Name, gender (inferred), email, current job, institution, dept., highest degree, PhD institution, advisor, field, year, interests.

Plus: All Basic fields plus publication count, 1st- and last-author counts, and up to three venue-specific counts.

Premium: All Plus fields plus a downloadable infographic visualization of the full applicant pool.

Can I hide some fields in the spreadsheet?

Yes. You can omit any field from the output — for instance, to remove doctoral institution or email address. These options are selected before downloading the spreadsheet.

Can I submit one big PDF containing many CVs?

No. CVParsa cannot split concatenated PDFs. Each applicant must have their own PDF file.

Can I submit DOCX or other non-PDF files?

No. CVParsa works with PDF files only at this time.

What languages and academic fields does CVParsa support?

CVParsa understands CVs in most major languages, recognizing international institutions and venues. Results are always returned in English.

All academic fields are supported. CVs in fields without standard publication formats (e.g. artistic performances) may return partial publication data.

Are multi-use or site licenses available?

Yes, including tax-exempt invoice payment for institutional partners. Contact licenses@cevianlabs.io.

How does CVParsa handle confidential information?

AES-256 encryption at rest. TLS in transit. Files never used to train AI models. Deleted after processing; originals retained ≤30 days for support only.

How accurate is CVParsa?

Academic CVs vary widely in format across fields. CVParsa uses domain-customized NLP to handle this variation. No automated tool is perfect.

In testing across hundreds of CVs in all disciplines, CVParsa achieves approximately 99% accuracy. In a batch of 100 CVs, you may see a few dozen extraction errors across all extracted fields combined.