pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

DocReward: A Document Reward Model for Structuring and Stylizing

cs.CV · 2025-10-13 · unverdicted · novelty 7.0

DocReward is a Bradley-Terry trained reward model on 117K paired documents across 32 domains that evaluates structural and stylistic professionalism independently of content, outperforming GPT-5 on benchmarks and guiding RL agents to higher-quality outputs.

citing papers explorer

Showing 1 of 1 citing paper.

  • DocReward: A Document Reward Model for Structuring and Stylizing cs.CV · 2025-10-13 · unverdicted · none · ref 19

    DocReward is a Bradley-Terry trained reward model on 117K paired documents across 32 domains that evaluates structural and stylistic professionalism independently of content, outperforming GPT-5 on benchmarks and guiding RL agents to higher-quality outputs.