On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “TabArena”

CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batchingcs.LG

CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching

problem Inference of tabular foundation models with large training datasets

method CRUMB (Clustered Retrieval Using Minimised-MMD Batching)

result CRUMB outperforms state-of-the-art context selection strategies on the TabArena benchmark

CRUMB PFN context selection covariate drift TabArena

2026-06-09abs ↗pdf ↗

The Manokhin Probability Matrix: A Diagnostic Framework for Classifier Probability Qualitystat.ML

A new framework separates classifier calibration and discrimination.

problem Combining reliability and resolution in probabilistic predictions.

method Manokhin Probability Matrix separates reliability and resolution using Spiegelhalter Z-statistic and AUC-ROC.

result Classifiers are categorized into four archetypes: Eagle, Bull, Sloth, and Mole.

classifier calibration probability quality Brier score post-hoc calibrators binary classification

2026-05-05abs ↗pdf ↗

TabPFN-3: Technical Reportcs.LG

TabPFN-3 scales tabular prediction models to large datasets and improves performance and speed.

problem Scaling tabular prediction models to large datasets with high performance and efficiency.

method Pretrained on synthetic data, introduces test-time compute scaling, and uses row-chunking.

result Significantly outperforms other models on TabArena and diverse datasets.

tabular prediction large datasets compute scaling model performance

2026-05-13abs ↗pdf ↗

Rank Intervals for Leaderboards: A Hierarchical Framework for Model Evaluationstat.ML

Hierarchical framework for model evaluation on leaderboards

problem Uncertainty and variability in model performance across tasks

method Hierarchical framework with task-level and leaderboard-level rank prediction intervals

result Statistically valid and informative model rank intervals

leaderboards model evaluation uncertainty rank intervals

2026-06-07abs ↗pdf ↗

TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Modelscs.LG

TabPFN-2.5 boosts tabular AI performance, especially for large datasets.

problem Improving tabular AI models for large datasets and complex feature sets.

method Advanced tabular foundation model with data augmentation and distillation techniques.

result TabPFN-2.5 outperforms tuned tree-based models and AutoGluon 1.4 on benchmark datasets.

tabular AI foundation models large datasets distillation XGBoost

2025-11-11abs ↗pdf ↗

Classifier Calibration at Scale: An Empirical Study of Model-Agnostic Post-Hoc Methodscs.LG

Study compares various calibration methods for binary classification tasks.

problem Improving probabilistic predictions in binary classification models.

method Benchmarked 21 classifiers using 5 calibration methods on real data.

result Venn-Abers predictors and Beta calibration show the largest log-loss reductions.

classifier calibration post-hoc methods binary classification tabular data model-agnostic

2026-01-19abs ↗pdf ↗