A duration-grouped, distribution-transformed multiplicative correction layer removes local watch-time prediction bias on top of frozen rankers, improving offline MAE/XAUC and online time spent.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
One empirical CDF table defines a bounded PIT coordinate, inverse-quantile base, and drift monitor, then SUN recovery multiplies a ratio head by that base to estimate original-space conditional means.
citing papers explorer
-
DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems
A duration-grouped, distribution-transformed multiplicative correction layer removes local watch-time prediction bias on top of frozen rankers, improving offline MAE/XAUC and online time spent.
-
PIT-SUN: A Deployable Empirical Marginal Transform Framework with Expectation-Consistent Recovery for Regression in Recommender Systems
One empirical CDF table defines a bounded PIT coordinate, inverse-quantile base, and drift monitor, then SUN recovery multiplies a ratio head by that base to estimate original-space conditional means.