KNOWWLTFM / Research
Research
From pre-training to a prediction.
The intended design separates learning across datasets from answering a question on your table.
- 01 · Pre-training
Learn shared patterns
Train a transformer across synthetic datasets to learn patterns that transfer between tasks.
What changesModel weights are learned.
- 02 · Inference
Use history as context
Supply observed states, transitions and related records. The pre-trained model uses that context to answer the question.
What changesThe input changes; weights stay fixed.
- 03 · Output
Report uncertainty
Return a prediction with an uncertainty band and reasons. When evidence is too weak, pass the case to the existing process.
What you receiveA score, its uncertainty and an explanation.
Entities, their state, their history and every transition.
A longitudinal table connects records through time. This synthetic supply chain shows how a change in one entity can affect related entities.
A PFN, out of the box, beat four hours of expert tuning in 2.8 seconds.
Hollmann et al., Nature 637 (2025)
Published PFN result. This does not measure LTFM performance.
Three stages to a new foundation model.
One model, built from the inside out. Each stage ships something real before the next begins.
Macro prediction
Calibrated calls on macro events from structured history.
LSM + Intelligence
The internal state of LTFM, shipped first to financial-services ML teams.
LTFM
The same core, generalised to every industry.
Tabular models are three years behind the LLM curve, and accelerating faster.
Model releases over time. The tabular timeline is shifted three years to sit on the same axis.
Tabular foundation models: same curve, three years later.
PRAGMA FM
A BERT-style foundation model on longitudinal banking transactions.
LTFM: longitudinal, calibrated, opinionated.
Every version makes the next one smarter.
Deployments show which patterns matter in real tasks. Those become better priors for the next round of pre-training.
25
papers, read & connected before we wrote a line of LTFM.
- PFNPrior-data fitted networks · Müller et al., 2022
- TabPFNTabular foundation model · Hollmann et al., Nature 2025
- TimesFM · Chronos-2Time-series foundation models
- KumoRFMRelational foundation model
…and more. We open research intake every 8 weeks. Researchers working on tabular or longitudinal models: write to contact@knoww.app.
What do you want to predict?
Every pilot starts in shadow mode. LTFM predicts on your cases next to what you use today and changes no decisions. Tell us what you want to predict and we'll reply with a pilot plan.