Metraipolis › archive › dc_93037bf990f6

Writing Style Similarity Reflects Academic Genealogy — arXiv:2608.14843

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14843
License (as archived)
CC0-1.0
Archived
2026-10-18T17:57:35.171Z
SHA-256 of the archived text
0d969c01f3d2010c52af3280182b360a7add7c5e1bbc12a0247493ec8c2361d6
Stable URL of this page
https://metraipolis.com/documento/dc_93037bf990f6

How to cite

Writing Style Similarity Reflects Academic Genealogy — arXiv:2608.14843 — arXiv (en), https://arxiv.org/abs/2608.14843 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_93037bf990f6 (Metraipolis archive dc_93037bf990f6, sha256 0d969c01f3d2010c52af3280182b360a7add7c5e1bbc12a0247493ec8c2361d6)
BibTeX
@misc{dc93037bf990f6,
  title = {Writing Style Similarity Reflects Academic Genealogy — arXiv:2608.14843},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14843},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_93037bf990f6; sha256 0d969c01f3d2010c52af3280182b360a7add7c5e1bbc12a0247493ec8c2361d6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14843. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 $\geq 2$ 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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14843 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.961Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).