AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

NAIPv2: Debiased Pairwise Learning for Efficient Paper Quality Estimation

Penghai Zhao, Jinyu Tian, Qinghua Xing, Xin Zhang, Zheng Li, Jianjun Qian, Ming-Ming Cheng, Xiang Li

ICLR 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Prediction-powered and conformal inference · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use debiased pairwise training instead of NAIPv1 regressionLLaMA-3 8B paper quality estimator · NAIDv2 testAUC: 0.605 -> 0.782Improved
use pairwise training with pointwise inference instead of pointwise training (ablation)NAIPv2 · NAIDv2 testAUC: 0.633 -> 0.782Improved
use pairwise training with pointwise inference instead of concatenated pairwise inference (ablation)NAIPv2 · NAIDv2 testAUC: 0.720 -> 0.782Improved
restrict pairs to same time and hierarchical cluster (ablation)NAIPv2 · NAIDv2 testAUC: 0.739 -> 0.782Improved
group pairs by publication time only (ablation)NAIPv2 · NAIDv2 testAUC: 0.739 -> 0.736No clear effect
group pairs by GPT-generated keywords (ablation)NAIPv2 · NAIDv2 testSpearman rho: 0.400 -> 0.007Hurt
use RTS instead of mean reviewer score as label (ablation)NAIPv2 · NAIDv2 testAUC: 0.753 -> 0.782Improved
use mode aggregation instead of mean (ablation)NAIPv2 · NAIDv2 testAUC: 0.753 -> 0.730Hurt
add curriculum learning from easy to hard pairs (ablation)NAIPv2 · NAIDv2 testAUC: 0.770 -> 0.782Improved
emphasize hard pairs (small RTS gap) (ablation)NAIPv2 · NAIDv2 testperformanceHurt
hierarchical cluster max distance too small or too large (ablation)NAIPv2 · NAIDv2 testperformanceHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy