document-understanding
latest
false
- Overview
- Getting started
- Activities
- Insights dashboards
- Document Understanding Process
- Quickstart tutorials
- Framework components
- ML packages
- Overview
- Document Understanding - ML package
- DocumentClassifier - ML package
- ML packages with OCR capabilities
- 1040 - ML package
- 1040 Schedule C - ML package
- 1040 Schedule D - ML package
- 1040 Schedule E - ML package
- 1040x - ML package
- 3949a - ML package
- 4506T - ML package
- 709 - ML package
- 941x - ML package
- 9465 - ML package
- ACORD125 - ML package
- ACORD126 - ML package
- ACORD131 - ML package
- ACORD140 - ML package
- ACORD25 - ML package
- Bank Statements - ML package
- Bills Of Lading - ML package
- Certificate of Incorporation - ML package
- Certificate of Origin - ML package
- Checks - ML package
- Children Product Certificate - ML package
- CMS 1500 - ML package
- EU Declaration of Conformity - ML package
- Financial Statements - ML package
- FM1003 - ML package
- I9 - ML package
- ID Cards - ML package
- Invoices - ML package
- Invoices Australia - ML package
- Invoices China - ML package
- Invoices Hebrew - ML package
- Invoices India - ML package
- Invoices Japan - ML package
- Invoices Shipping - ML package
- Packing Lists - ML package
- Payslips - ML package
- Passports - ML package
- Purchase Orders - ML package
- Receipts - ML package
- Remittance Advices - ML package
- UB04 - ML package
- Utility Bills - ML package
- Vehicle Titles - ML package
- W2 - ML package
- W9 - ML package
- Other Out-of-the-box ML Packages
- Public endpoints
- Traffic limitations
- OCR Configuration
- Pipelines
- OCR services
- Supported languages
- Deep Learning
- Data and security
- Licensing
Document Understanding User Guide
Last updated Oct 15, 2025
IRS Form 3949-A, Information Referral, is used to report suspected tax violations, such as fraud or tax evasion, to the IRS. Form 3949-A plays a critical role in facilitating the detection and investigation of tax-related crimes, ensuring fairness and integrity in the tax system.
This ML package is trained on 31 regular data fields to extract the relevant data points from Form 3949-A.
This model was trained on all versions released by the IRS from January 2017 to present.
The ML package is trained to automatically detect data such as:
- Document Version
- Individual Name, SSN, DoB, Address, Occupation
- Business Address, Email, Website
- Unreported Tax Year, Unreported Tax Amount
- Bank Name, Address
- Reporter Name, Phone
You can download the a sample filled-in form from here.
You can also preview the sample of a filled-in form:
