CalibratedDecisions.

Repo · Data & extraction

tax-doc-classifier

TypeScript library that classifies tax-document PDF pages into IRS forms and page kinds with TypeSafe Jev Choice questions over a shipped JSON…

Open github.com ↗

From the repository

Tax document page classifier built on Jev decisions. 100% strict accuracy across 261 IRS forms, ~$0.001 per page.

How builders describe it

TypeScript library that classifies tax-document PDF pages into IRS forms and page kinds with TypeSafe Jev Choice questions over a shipped JSON criteria file (261 forms)—no fine-tuned model hosted by the project.
Text-only classifier for 261 federal tax forms that sends each PDF page's text to Jev, which returns a probability over forms and page kinds behind a confidence gate; no model is trained.

The decision Jev makes

Keep or drop a row, assign a label, or select one field value at a time.

Where it fits

Putting Jev next to the data: filtering rows with plain-English conditions, classifying records, labelling datasets and pulling structure out of text one small decision at a time. All 98 data & extraction projects →

Related projects