# Writing Style Similarity Reflects Academic Genealogy

arXiv: https://arxiv.org/abs/2608.14843 · HTML: https://mlsanity.com/paper/2608.14843/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 10 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 2 of 2)

- [StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples](https://mlsanity.com/paper/2410.12757/) (2024)
- [A Computational Model For Individual Scholars' Writing Style Dynamics](https://mlsanity.com/paper/2305.04900/) (2023)

## Abstract (arXiv)

As authorship attribution systems are increasingly deployed to detect ghostwritten and AI-generated papers, their errors can support accusations against legitimate authors. These systems conflate stylistic similarity with individual identity. Researchers, however, study under advisors, and inherit their stylistic quirks. We build a corpus of arXiv authors with ≥ 2 solo papers from the Mathematics Genealogy Project graph, giving 5,803 total authors and 2,501 ground-truth advisor-student pairings. Using embeddings from a fine-tuned model, advisors sit 39.9% closer in cosine distance to their students than a random same-field author does. Using two open models, we reproduce the effect at 12.6% and 14.5%. Academic siblings, two students of one advisor who may never have met, sit 30.4% closer across 8,360 pairs, even when they studied at different institutions. Pairs who share only institution and field show negligible similarity. Given a closed-set attribution task over the same corpus, the system's errors occur on the true author's advisor, student, academic sibling, or lab mate 11 times more often than chance.