Work

Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches

Year: 2026

Type: conference-paper

Abstract: Reproducing computational research is often treated as a straightforward matter of re-running shared code on shared data. In practice, published analyses frequently fail even when materials are available, due to missing dependencies, brittle paths, version mismatches, and—more challenging—gaps in analytical logic. We investigate whether large language models (LLMs) and agentic AI systems can automate the routine but labor-intensive work of repairing such failures, thereby lowering the practical barrier to computational verification.

Source: International World Wide Web Conference (WWW)

DOI: 10.1145/3774905.3795485

Authors: Syed Mehtab Hussain Shah, Frank Hopfgartner, Arnim Bleier

Institutions: GESIS - Leibniz Institute for the Social Sciences, Universität Koblenz

Language: English

Topic: Scientific Computing and Data Management

Subfield: Information Systems and Management

Field: Decision Sciences

Domain: Social Sciences

Open Access status: hybrid

OpenAlex ID: W7155606551

FWCI: 13.94

Cites: 26

Cited by: 3

Related to: 10