Author

Yuvraj Verma

h-index 1 View on Semantic Scholar

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Exact Dice Degradation Envelopes for Label-Free Segmentation Update Selection

Test-time segmentation updates can improve an unlabeled input while damaging another. Confidence and transformation consistency can rank candidates, but do not in themselves bound the loss caused by returning a changed mask. We derive the exact largest decrease in binary Dice between a baseline and a candidate, maximiz...

Yuvraj Verma · 0 citations

#machine learning Preprint Jul 2026

What Does 99% Accuracy Measure? A Reproducible Audit of Shortcut Learning in a Widely Used Fake News Corpus

Text classifiers trained on the ISOT/Kaggle "Fake and Real News"corpus routinely report accuracy and F1 above 0.98, which concludes that within-corpus scores here quantify source and topic separability rather than veracity, and is recommended metadata-only, small-sample, and topic-disjoint baselines as inexpensive diag...

Yuvraj Verma · 0 citations

Jul 2026

Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models

It is argued that this comparison of matched-budget retry conditions confounds the value of the feedback with the value of the extra attempt, and that anchoring is the cost of committing to a bad first attempt.

Yuvraj Verma · arXiv.org · 1 citation · ⚡1