Skip to main content

Paper Pipeline

The paper pipeline is a structured workflow that takes raw experiment results and produces publication-ready manuscripts. Every step is assisted by agents, reviewed across models, and tracked with full version history.

Pipeline Stages

1

Evidence Collection

As experiments complete, their results are tagged for inclusion in specific paper sections. The system maintains a mapping from experiment IDs to paper sections.
2

Claims Lock

Before drafting begins, the Paper Lead produces a claims table, every scientific assertion the paper will make, linked to its supporting evidence. No claim can exist without an experiment or derivation backing it.
3

Outline

An outline is generated from the claims table. Each section gets a scope: what claims it contains, what figures it needs, and what prior work it must cite.
4

Drafting

Agents draft sections in parallel. The Research Lead writes methods and results. The Paper Lead handles introduction and discussion. Workers generate tables and format equations.
5

Cross-Model Review

The full manuscript is reviewed by AI models from at least two different providers. Reviews are structured: accuracy, completeness, clarity, overclaiming, missing citations.
6

Revision

Based on review feedback, agents revise the manuscript. Each revision round produces a diff showing what changed and why. The revision tracker logs every round.
7

Compilation

LaTeX source is compiled to PDF using revtex4-2. The system verifies: zero undefined references, all figures embedded, correct page count, proper bibliography.
8

Submission Package

The final package includes: PDF, LaTeX source, figures, bibliography, supplementary data, and a cover letter. Ready for arXiv upload.

LaTeX Compilation

All papers use revtex4-2 (Physical Review D format):
Compilation runs on GPU pods with texlive-publishers installed:
Common pitfalls: Do not use aastex631. Do not use \citep/\citet (use \cite{}). Do not use deluxetable (use ruledtabular). Figures must be in the same directory as the .tex file.

Figure Management

Figures are auto-generated from experiment outputs and linked to papers:

Version History

Every change is versioned:

Readiness Dashboard

The paper readiness dashboard tracks progress across six dimensions:

CLI