NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#concept-bottleneck

1 stories this week · 1 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedinterpretability1 ood-detection1 self-supervised1 time-series1

2 stories, newest first · one card per story

Hugging Face daily papers5d ago

ConceptTime uses predictive surprise to interpret time-series classifiers

A frozen forecaster's prediction error both segments series and builds concepts, with no labels, language model, or expert vocabulary.

time-series interpretability

arXiv cs.AI / cs.LG / cs.CLSep 28, 2026

DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detection

DF-CBM is a region-aware concept bottleneck model that explains deepfake decisions with spatially grounded manipulation concepts.

deepfake explainability

1