@article{besrour-farber-2026-unarxive,
    title = "unar{X}ive 2024: A Large-Scale Scientific Corpus for Citation-Aware Retrieval and Generation",
    author = {Besrour, Ines  and
      F{\"a}rber, Michael},
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.556/",
    pages = "6990--6997",
    abstract = "Full-text collections of scientific papers are essential for NLP research and the training of language models. However, existing resources remain incomplete: they often lag behind the fast-paced growth of scientific publishing, lack comprehensive citation networks, and discard essential structural elements. In this work, we introduce unarXive 2024, a large-scale, richly structured corpus containing every arXiv submission from January 1991 to December 2024 {--} over 2.28 million documents across physics, mathematics, computer science, and other fields. Our release enhances each paper with detailed metadata, reconstructs a substantially more complete citation network than existing datasets, and preserves fine-grained structural information, including section boundaries, mathematical notation, and non-textual elements. Beyond the corpus itself, we provide dense and sparse indexes optimized for retrieval-augmented generation (RAG) over the full arXiv archive. All resources, including code and data, are publicly available: https://github.com/faerber-lab/unarXive-2024"
}