pith. sign in

Op- timizing the CVaR via sampling

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Training ML Models with Predictable Failures

cs.LG · 2026-05-14 · unverdicted · novelty 5.0

A finite-k decomposition reveals a bias toward over-prediction in failure rate extrapolation from evaluation data, addressed by a new forecastability loss that improves held-out forecast accuracy in language-model and RL experiments.

citing papers explorer

Showing 1 of 1 citing paper.

  • Training ML Models with Predictable Failures cs.LG · 2026-05-14 · unverdicted · none · ref 40

    A finite-k decomposition reveals a bias toward over-prediction in failure rate extrapolation from evaluation data, addressed by a new forecastability loss that improves held-out forecast accuracy in language-model and RL experiments.