Saved in:
Bibliographic Details
Main Authors: Cao, Haotian, Merz, Garrett, Cranmer, Kyle, Shiu, Gary
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.01072
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917454126514176
author Cao, Haotian
Merz, Garrett
Cranmer, Kyle
Shiu, Gary
author_facet Cao, Haotian
Merz, Garrett
Cranmer, Kyle
Shiu, Gary
contents We study the use of transformers to reconstruct the compositions of tensor products of two-dimensional rational conformal field theories (RCFTs) based on their low-energy spectra. The task is challenging due to its combinatorial nature. The constituent theories are characterized by their central charges and affine Lie algebra labels. We achieve 98% accuracy in recovering the constituents of tensor products theories constructed from Wess-Zumino-Witten models. We further demonstrate that our method generalizes to CFTs with larger central charge and unseen classes of RCFTs by adding a small number of out-of-domain examples. Our results show that transformers are effective at this task and point towards a new tool for bulk reconstruction in AdS/CFT.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01072
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reconstructing conformal field theoretical compositions with Transformers
Cao, Haotian
Merz, Garrett
Cranmer, Kyle
Shiu, Gary
High Energy Physics - Theory
Machine Learning
We study the use of transformers to reconstruct the compositions of tensor products of two-dimensional rational conformal field theories (RCFTs) based on their low-energy spectra. The task is challenging due to its combinatorial nature. The constituent theories are characterized by their central charges and affine Lie algebra labels. We achieve 98% accuracy in recovering the constituents of tensor products theories constructed from Wess-Zumino-Witten models. We further demonstrate that our method generalizes to CFTs with larger central charge and unseen classes of RCFTs by adding a small number of out-of-domain examples. Our results show that transformers are effective at this task and point towards a new tool for bulk reconstruction in AdS/CFT.
title Reconstructing conformal field theoretical compositions with Transformers
topic High Energy Physics - Theory
Machine Learning
url https://arxiv.org/abs/2605.01072