A tabular foundation model, pretrained. No tuning. With the evidence to ship it to production.
TabICL is the open tabular foundation model from soda-inria, pretrained on millions of synthetic tables and competitive with heavily tuned XGBoost, CatBoost, and LightGBM out of the box. Skore turns its output into evidence you can present to a regulator, a CEO, or a peer reviewer.
Tabular foundation models are not replacing classical ML.
TabICL is the natural endpoint of a twenty-year program. Scikit-learn democratized tabular ML with fit and predict. skrub absorbs the mess of real-world data. TabICL makes the fitting step optional. Skore turns the output into evidence.
TabICL gives you a pretrained model. Skore gives you the evidence to ship it to production.
A pretrained foundation model shifts the burden. The question is no longer “did my hyperparameter search converge?”, it is “does this pretrained behaviour hold on my data, my regulator, my edge cases?”
The same problem. Two pipelines. Two visions of tabular ML.
On the left, the careful 2025 baseline: tune your gradient boosting, persist what worked. On the right, what 2026 looks like: call a foundation model, persist the evidence.
One narrative arc. Five examples.
Each demo is a runnable notebook benchmarking TabICL against scikit-learn's HistGradientBoostingClassifier, with Skore as the comparison layer.
The five-minute model
”Hyperparameter tuning is a tax. Foundation models pay it once, for everyone.”
HGBT default vs HGBT + 100 Optuna trials vs TabICL default. Skore’s ComparisonReport renders accuracy versus wall-clock time. The orange bar lands at the same accuracy as the tuned baseline, in a fraction of the compute.
Dirty data, clean prediction
“Real data is messy. Tools should hide the mess. skrub absorbs the dirt; TabICL ingests what’s left.”
Mixed strings, dates, high-cardinality categoricals. Three pipelines: HGBT manual, TableVectorizer
- HGBT, TableVectorizer + TabICL. Skore breaks down per-column contribution.
Calibrated probabilities for risk
”In high-stakes decisions, calibration is the product.”
Probabilistic classification on imbalanced data. Skore’s calibration view: reliability diagrams, ECE/MCE, and 2D probability surfaces side-by-side.
Quantile regression, single fit
”Distributions, not point predictions, are the language of risk.”
HGBT trains N models for N quantiles. TabICL emits the full predictive distribution from a single fit. Skore renders coverage and pinball loss.
Small data, strong prior
”When data is scarce, the prior is everything. Foundation models bring a free one.”
Sweep training sizes from 50 to 5,000. HGBT collapses below ~300; TabICL’s pre-training acts as a free strong prior. Skore plots learning curves with confidence bands.
Three pip installs. One scikit-learn API.
Install the open stack from PyPI, drop it into any scikit-learn pipeline, and start with the worked notebooks.
Deploying TabICL in a regulated environment?
Probabl offers Forward Deployed Engineering engagements for teams structuring tabular ML around foundation models. Our Design Partner Program is now starting its second cohort, with priority access to the TabICL team.
