Quantifying the Reconstructability of Astrophysical Methods with Large Language Models and Information Theory: A Case Study in Spectral Reconstruction

arXiv 2026 34.2 method

TLDR

An information-theoretic framework using LLMs to quantify how well astrophysical methods can be reconstructed from text, revealing an entropy floor limiting reproducibility.

Reasoning

Strengths: Novel combination of information theory and LLMs to assess reproducibility, with a concrete case study and executable pipelines. Weaknesses: Limited to a single case study (TNO spectral reconstruction) and does not address broader generalization or tacit knowledge capture.

Read-first score

Read-first score 34.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 24.

Recency 8%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=analysis,result

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Topical relevance 42%

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Field roles

FrontierBridge

Rank sensitivity

Stability: volatile; rank range: 45.

Keyword Scores

AI for scientific research

automated research

automated scientific discovery

research automation

AI scientist

automated experimentation

scientific discovery agent

autonomous research agent

experiment design agent

literature review agent

survey generation

paper writing agent

Resources

Paper