CalibratedDecisions.

Post · Data & extraction

tab-jev

A Jev-like model paired with a tabular foundation model.

Open x.com ↗
Jerry Xu @jerrycxu

tab-jev: jev-like model + tabular foundation model = an in-context learner for your text & tabular data.

github.com/edamame-labs/t…

Many real industry datasets are a mix of tabular and text data:
- Tabular foundation models like TabPFN learn from a few hundred labeled rows in

Video from the post

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