What Does 99% Accuracy Measure? A Reproducible Audit of Shortcut Learning in a Widely Used Fake News Corpus
arXiv:2609.25006v1 Announce Type: new Abstract: Text classifiers trained on the ISOT/Kaggle "Fake and Real News" corpus routinely report accuracy and F1 above 0.98, a level of performance that sits uneasily beside the difficulty of assessing veracity. Using a transparent TF-IDF and linear-classifie…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-23 04:00 · arXiv cs.CL
What Does 99% Accuracy Measure? A Reproducible Audit of Shortcut Learning in a Widely Used Fake News Corpus