The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The study audited ten different classifiers—including linear, tree‑ensemble, neural, glass‑box, and tabular foundation models—on national health survey data to predict myocardial infarction. By systematically removing features that could cause target leakage, the authors found that all models’ AUROC scores collapsed into a narrow band, indicating that reported high accuracy in prior work was largely due to leakage rather than model sophistication. The glass‑box explainable boosting machine performed comparably to other models while being much faster, and the authors demonstrated that fairness, calibration, and uncertainty can be audited and repaired without sacrificing performance.
arXiv:2606. 20115v3 Announce Type: replace Abstract: Conformal risk control (CRC) provides distribution-free segmentation guarantees by calibrating a prediction-set threshold on held-out data.
DeepGOF-1 is a neural goodness‑of‑fit test for logistic regression that maps residuals over covariate ranks, scores them with a frozen convolutional network, and calibrates the score via parametric bootstrap. It achieves first‑order valid level, offers explicit local power, and outperforms traditional chi‑square and projection tests in simulations and real data, revealing missed interactions and guiding model repairs. In the SUPPORT study, it identified a U‑shaped risk pattern for blood pressure and respiratory rate that standard calibration curves obscured, and it ran in 13 seconds versus hours for competing methods.
arXiv:2607. 19526v1 Announce Type: new Abstract: "Stop Chasing the C-index when Evaluating Survival Analysis Models" (ICML 2026, Spotlight) argued normatively, on synthetic data, that evaluating survival models by discrimination alone, i.
This systematic review and meta‑analysis examined 48 machine‑learning studies that predict live‑birth outcomes after IVF/ICSI using routine clinical data. The pooled discrimination of internally validated models was an AUC of 0.814, while externally validated models had an AUC of 0.756, with no significant difference between them. Most studies (47/48) were at high or unclear risk of bias, only four assessed calibration, and none demonstrated clinical impact, leading to a low‑to‑very‑low certainty of evidence.
The paper introduces a missingness‑aware conformal calibration method for mortality prediction that accounts for cross‑hospital distribution shifts. By selecting a measurement on an independent sample, grouping patients by whether that measurement is recorded, and applying Mondrian calibration within each group, the method avoids reusing calibration outcomes. Experiments on eICU and MIMIC‑IV data show that, compared to pooled calibration, it reduces the worst‑group coverage gap by a median of 1.9 percentage points across six settings, though the benefit varies with predictor and hospital.