Towards LLM-Powered Automation of a Dark Matter Constraint Repository
Abstract
Dark matter constraint repositories are critical community infrastructure, yet the most widely-used are volunteer-maintained, a sustainability risk as results accelerate. Limits are typically published as figures rather than machine-readable records, compounding the burden. We present a large language model (LLM) pipeline that monitors arXiv, extracts limit curves, integrates them as code, and opens pull requests for human review. On a 329-paper benchmark of measured limits graded against the upstream-curated repository, it identifies the coupling type for 98.1% of gradable papers. The 81% yielding a comparable extraction reach a median residual of 0.17 dex from a single model read, and 51% of all papers land within a factor of two of the curator's curve. The LLM is confined to perception; arithmetic, unit conversion, and the guards that reject mis-extractions are deterministic, testable code. Deployed, the pipeline has generated limit proposals, but none have merged: governance of AI-generated scientific data is itself unsolved.
Related
- Constraint on particle mass of dark matter based on XTE J1814-338 observation and DANS model
- Cosmological extra dimensions can mimic dark matter I. Dark matter in galaxies
- JWST lensed quasar dark matter survey. IV. Stringent warm dark matter constraints from the joint reconstruction of extended lensed arcs and quasar flux ratios
- Dark matter density profiles of the Milky Way satellite population: Reconciling simulations and observations
- Strong-lensing perturber signatures in self-interacting dark matter simulations
BibTeX
@misc{yuan2026towards,
title = {{Towards LLM-Powered Automation of a Dark Matter Constraint Repository}},
author = {Lanqing Yuan and Karthik Ramanathan},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.21658},
eprint = {2606.21658},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.21658},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Towards LLM-Powered Automation of a Dark Matter Constraint Repository
AU - Lanqing Yuan
AU - Karthik Ramanathan
PY - 2026
DA - 2026/09/09
PB - arXiv
DO - 10.48550/arxiv.2606.21658
UR - https://arxiv.org/abs/2606.21658
AB - Dark matter constraint repositories are critical community infrastructure, yet the most widely-used are volunteer-maintained, a sustainability risk as results accelerate. Limits are typically published as figures rather than machine-readable records, compounding the burden. We present a large language model (LLM) pipeline that monitors arXiv, extracts limit curves, integrates them as code, and opens pull requests for human review. On a 329-paper benchmark of measured limits graded against the upstream-curated repository, it identifies the coupling type for 98.1% of gradable papers. The 81% yielding a comparable extraction reach a median residual of 0.17 dex from a single model read, and 51% of all papers land within a factor of two of the curator's curve. The LLM is confined to perception; arithmetic, unit conversion, and the guards that reject mis-extractions are deterministic, testable code. Deployed, the pipeline has generated limit proposals, but none have merged: governance of AI-generated scientific data is itself unsolved.
ER -