Skip to main content
Search

Hare Krishna

1 related articles

Subscribe to updates
  1. arXiv

    Resample the corpus, how much do predictions move? Smoothing cuts disagreement only 5–40%, far short of the 75% scaling implies

    A first-order formula predicts how much a masked-text reconstructor's outputs would change if a second corpus were collected from the same population, using only an independent reference corpus and treating each document as one sampling unit. On TinyStories, WikiText-103 and CNN/DailyMail, growing the corpus from 512 to 2,048 chunks lowers measured disagreement by only 5–40%, far short of the 75% implied by inverse-size scaling, and the forecast tracks that slow decline. Small references systematically underpredict disagreement, and a source-split jackknife that uses only reference data reduces this calibration error by 57–59%.

You’re all caught up