PEARL approximates unbiased percentile-based preference signals via nonparametric contrastive pairwise comparisons and bootstrapping, yielding gains in watch duration, consumption, and interaction rate on a large livestream platform.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation
PEARL approximates unbiased percentile-based preference signals via nonparametric contrastive pairwise comparisons and bootstrapping, yielding gains in watch duration, consumption, and interaction rate on a large livestream platform.