Metraipolis › archive › dc_3f01e18fbe43
A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization — arXiv:2609.38161
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38161
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:32:08.568Z
- SHA-256 of the archived text
5226f8f9bbcce680e354f7f075888537079d7640c2c237daf39e3d723303fc4f- Stable URL of this page
https://metraipolis.com/documento/dc_3f01e18fbe43
How to cite
A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization — arXiv:2609.38161 — arXiv (en), https://arxiv.org/abs/2609.38161 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f01e18fbe43 (Metraipolis archive dc_3f01e18fbe43, sha256 5226f8f9bbcce680e354f7f075888537079d7640c2c237daf39e3d723303fc4f)
BibTeX
@misc{dc3f01e18fbe43,
title = {A Spectral Theory of Distortion in LLM Graph Reconstruction: Sharp Bounds and Empirical Characterization — arXiv:2609.38161},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38161},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f01e18fbe43; sha256 5226f8f9bbcce680e354f7f075888537079d7640c2c237daf39e3d723303fc4f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38161. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Evaluations of graph reconstruction by language models typically report a single aggregate distance between the original and the reconstructed graph. We prove that for the Wasserstein distance between Laplacian spectra such a summary is bracketed by two edge counts, the net change in edge number from below and the symmetric difference from above, each scaled by $2/n$ where $n$ is the number of vertices. The bracket is sharp: its two ends coincide exactly when the reconstruction only adds edges or only deletes them, and on that class the distance is a rescaled edge count that says nothing about which edges changed. When the ends differ, the residual between the distance and the lower end is positive only if the reconstruction both invented and lost edges, which turns it into a certificate of mixed editing computable from the reported summaries alone. We characterize these regimes in 135 reconstructions produced by three open-weight models over 45 synthetic graphs. Seventy-seven outputs are one-sided and 29 mixed outputs have $X > 0$, including cases where edge count is exactly preserved while nineteen edges were simultaneously invented and lost. The three models differ in editing policy, ranging from copying the input to attempting completion at the cost of large hallucination volume, a distinction that aggregate distortion does not reveal. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Discrete Mathematics (cs.DM). Pagina del lavoro: https://arxiv.org/abs/2609.38161 — 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 2026-10-07T16:59:48.434Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).