Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data.
Leakage and the reproducibility crisis in machine-learning-based science
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
Complex multimodal architectures do not reliably outperform unimodal baselines or a simple multimodal baseline under standardized evaluation.
SurvBench supplies a configurable, open-source preprocessing pipeline that standardizes multi-modal EHR data from four critical-care databases for single-risk and competing-risk survival analysis.
Proposes bearing-wise data partitioning to remove leakage in ML bearing fault diagnosis, reformulates as multi-label classification, and shows training bearing count drives generalization on four public datasets.
LSTM networks predict HRRR forecast errors with average improvements of 48% for precipitation, 25% for temperature, and 15% for wind using mesonet ground truth.
fastml is an R package that enforces leakage-free preprocessing through guarded resampling and provides a unified interface for safer automated ML including survival analysis.
citing papers explorer
-
Neural Point-Forms
Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data.
-
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
-
Fusion or Confusion? Multimodal Complexity Is Not All You Need
Complex multimodal architectures do not reliably outperform unimodal baselines or a simple multimodal baseline under standardized evaluation.
-
SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis
SurvBench supplies a configurable, open-source preprocessing pipeline that standardizes multi-modal EHR data from four critical-care databases for single-risk and competing-risk survival analysis.
-
Towards a more realistic evaluation of machine learning models for bearing fault diagnosis
Proposes bearing-wise data partitioning to remove leakage in ML bearing fault diagnosis, reformulates as multi-label classification, and shows training bearing count drives generalization on four public datasets.
-
Predicting Forecast Error for the HRRR Using LSTM Neural Networks: A Comparative Study Using New York and Oklahoma State Mesonets
LSTM networks predict HRRR forecast errors with average improvements of 48% for precipitation, 25% for temperature, and 15% for wind using mesonet ground truth.
-
fastml: Guarded Resampling Workflows for Safer Automated Machine Learning in R
fastml is an R package that enforces leakage-free preprocessing through guarded resampling and provides a unified interface for safer automated ML including survival analysis.