astro-hep-bert

Model Card for Astro-HEP-BERT

Astro-HEP-BERT is a bidirectional transformer designed primarily to generate contextualized word embeddings for computational conceptual analysis in astrophysics and high-energy physics (HEP). Built upon Google's bert-base-uncased, the model underwent additional training for three epochs using the <a target="_blank" rel="noopener noreferrer" href="https://huggingface.co/datasets/arnosimons/astro-hep-corpus">Astro-HEP Corpus</a>, containing 21.84 million paragraphs found in more than 600,000 scholarly articles sourced from arXiv, all pertaining to astrophysics and/or high-energy physics. The sole training objective was Masked Language Modeling (MLM).

To optimize the model's ability to embed domain-specific language, training was conducted exclusively on entire paragraphs, rather than packing in as many sentences as possible, as often suggested in BERT tutorials. This "full-paragraphs format" preserves sentences within their original context, which is especially meaningful in academic writing where paragraphs focus on one idea.

The Astro-HEP-BERT project demonstrates the general feasibility of training a customized bidirectional transformer for computational conceptual analysis in the history, philosophy, and sociology of science as an open-source endeavor that does not require a substantial budget. Leveraging only freely available code, weights, and text inputs, the entire training process was conducted on a single MacBook Pro Laptop (M2/96GB).

For further insights into the model, the corpus, and the underlying research project (<a target="_blank" rel="noopener noreferrer" href="https://doi.org/10.3030/101044932" >Network Epistemology in Practice</a>) please refer to the following three papers:

1. <a target="_blank" rel="noopener noreferrer" href="https://arxiv.org/abs/2411.14877">Simons, A (2024). Astro-HEP-BERT: A bidirectional language model for studying the meanings of concepts in astrophysics and high energy physics. arXiv:2411.14877.</a>

2. <a target="_blank" rel="noopener noreferrer" href="https://arxiv.org/abs/2411.14073">Simons, A (2024). Meaning at the planck scale? Contextualized word embeddings for doing history, philosophy, and sociology of science. arXiv:2411.14073.</a>

3. <a target="_blank" rel="noopener noreferrer" href="https://arxiv.org/abs/2506.12242">Simons, A; Zichert, M; and Wüthrich, A (2025). Large Language Models for History, Philosophy, and Sociology of Science: Interpretive Uses, Methodological Challenges, and Critical Perspectives. arXiv:2506.12242.</a>

Model Details

• Developer: <a target="_blank" rel="noopener noreferrer" href="https://www.tu.berlin/en/hps-mod-sci/arno-simons">Arno Simons</a>
• Funded by: The European Union under Grant agreement ID: <a target="_blank" rel="noopener noreferrer" href="https://doi.org/10.3030/101044932" >101044932</a>
• Language (NLP): English
• License: apache-2.0
• Parent model: Google's <a target="_blank" rel="noopener noreferrer" href="https://github.com/google-research/bert">bert-base-uncased</a>

<!--- ## How to Get Started with the Model Use the code below to get started with the model. [Coming soon] ## Citation **BibTeX:** [Coming soon] **APA:** [Coming soon] -->