dorsal/arxiv
View SchemaString Theory from Infinite Width Neural Networks
| Authors | Samuel Frank, James Halverson |
|---|---|
| Categories | |
| ArXiv ID | 2601.06249vv1 |
| URL | https://arxiv.org/abs/2601.06249 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
We realize bosonic string theory with ensembles of infinite width neural networks. The string tension is tuned by the variance of the output weights. The construction provides a new computation of the foundational Virasoro-Shapiro and Veneziano amplitudes as neural network correlators.
{
"annotation_id": "c079c5b0-a76b-4634-81fe-8bdb1b6b9114",
"date_created": "2026-02-17T05:53:08.670000Z",
"date_modified": "2026-02-17T05:53:08.670000Z",
"file_hash": "f329cd16a50555a07ee77d768626d1102d6198ffa509893e1a363d30f086075f",
"private": false,
"record": {
"abstract": "We realize bosonic string theory with ensembles of infinite width neural networks. The string tension is tuned by the variance of the output weights. The construction provides a new computation of the foundational Virasoro-Shapiro and Veneziano amplitudes as neural network correlators.",
"arxiv_id": "2601.06249",
"authors": [
"Samuel Frank",
"James Halverson"
],
"categories": [
"hep-th"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "String Theory from Infinite Width Neural Networks",
"url": "https://arxiv.org/abs/2601.06249",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "0de551bd-78d7-40e0-a324-7f4b4a58547c",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}