paper-autoraters

Community

Automated quality scoring for research papers

AuthorAr9av
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates rigorous, reproducible scoring of research paper drafts so authors and evaluation pipelines can quantify literature-review quality, citation fidelity, and holistic paper quality without manual rubric application.

Core Features & Use Cases

  • Citation F1 Partitioning: Partition references into P0/P1 priority buckets and deterministically compute Precision/Recall/F1 against ground-truth via Semantic Scholar ID resolution.
  • Literature Review Quality (6-axis): Produce conservative, evidence-based 6-axis JSON scores with penalties and an overall score for Intro + Related Work.
  • Side-by-Side (SxS) Comparisons: Run dual-order SxS judgments for full-paper and literature-review-only comparisons to mitigate positional bias.
  • Use Case: Validate a paper-generating pipeline by scoring generated drafts against a ground-truth paper, compare two pipeline outputs, or audit literature-review improvements across iterations.

Quick Start

Run the autoraters to score the draft 'submission_v1.pdf' against the ground-truth 'paper_gt.pdf' and produce JSON reports.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: paper-autoraters
Download link: https://github.com/Ar9av/PaperOrchestra/archive/main.zip#paper-autoraters

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.