kyotofin/tax-doc-classifier
Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
A tax document classifier built with Jev. We ingest thousands of tax documents using an LLM pipeline built last tax season. Jev classifies 100% of our tax document corpus at $0.001 per page — 34× cheaper and 6× faster than that LLM setup. This is the classifier, open sourced. One request per page. The page's text goes to Jev, TypeSafe's decision model, which returns a probability over 261 IRS forms and 7 page kinds instead of text. No model is trained and nothing is hosted: the classifier is a JSON file describing each form, generated from the IRS's own PDFs. No model is trained and nothing is hosted. The classifier is a JSON file of form descriptions (data/criteria.json) and a decision model that reads a page and picks from them. The decision model is TypeSafe Jev, a System One model that returns a probability over options instead of text. or…
Read the full README ↗ · Preview checked 2026-11-03T03:02:19.326Z
Inside the original README — Document outline
- tax-doc-classifier
- Setup
- Results
- Against the LLM setup it replaces
- How it works
- Page kinds
- Form ids
- The data file
- Evaluation
- Plugging in another model
- Limits
- Requirements
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.
Repository facts
- Owner
- kyotofin
- Primary language
- TypeScript
- Stars
- 449
- Forks
- 61
- Open issues + pull requests
- 2
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-09-18T14:40:45.000Z
- Last push
- 2026-09-20T10:34:47.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-09-25T12:03:43.116Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.