research-paper-writing

Automating machine learning experiment design and paper writing requires an iterative pipeline that manages the feedback loop between empirical results and LaTeX manuscript revisions. This Skill unifies experiment execution, structured logging, and drafting to prevent disconnected narratives.

Preventing hallucinated citations in BibTeX entries requires programmatic validation against academic databases. This Skill fetches and verifies references using Semantic Scholar and arXiv to ensure every citation in your LaTeX draft is accurate and reproducible.

Yes, the research pipeline supports iterative feedback between experiment results and manuscript revisions. It manages the end-to-end lifecycle, allowing you to loop between empirical analysis and LaTeX drafting until claims are fully supported for top-tier AI conferences.

Yes, you can generate reproducible plots for your machine learning paper. The Skill leverages matplotlib and SciencePlots alongside scipy and numpy for experiment execution, ensuring your empirical results are visually structured and ready for LaTeX integration.

The best way to manage the lifecycle for a NeurIPS or ICML paper is using a unified workspace that handles everything from initial literature review to final LaTeX drafting. This Skill automates experiment setup, citation verification, and iterative manuscript updates.

Yes, you need Semantic Scholar and arXiv access to validate references. The Skill integrates these dependencies through the habanero and requests libraries to programmatically fetch and verify BibTeX entries, ensuring citation reproducibility for your manuscript.