arXiv subjects

Tobias Holtdirk

Publications and source records attributed to Tobias Holtdirk.

5 recordsLinked to original sources

arXiv2026

Automated reproducibility assessments in the social and behavioral sciences using large language models

Reproducibility in the social and behavioral sciences is typically evaluated by independent researchers who reanalyze the original data to assess whether the published findings can be recovered. However, such approaches are resource-intensive and difficult to scale. Here, we show that large language models (LLMs) can automate reproducibility assessments. Using N = 180 published studies with predefined claims from the behavioral and social sciences, we compare LLM-generated analyses with the original findings. For 11 studies, the LLM pipeline could not produce a viable effect size estimate. For the remaining studies, the LLM reached the same qualitative conclusion as the original study in 80% of cases, and recovered the original effect sizes (using a +/-0.05 tolerance in Cohen's d) in 24% of studies. In a subset with human reanalyses, the LLM reached the same qualitative conclusion as the original study in 95% of studies, similar to human reanalysts (83%), and the LLM recovered the original effect sizes using a +/-0.05 tolerance in 40% of studies, again broadly similar to human reanalysts (28%). Given the current capabilities and limitations of LLMs, the findings show that LLMs can support systematic audits of empirical results rather than substitute expert judgment. As such, LLMs can serve as a scalable screening tool to improve the rigor and reproducibility in empirical research.

cs.AI↗

arXiv2026

In-Context Learning for the Imputation of Public Opinion Data with Large Language Models

Large language models have been widely evaluated as simulators of individual survey responses. In practice, however, fully unobserved responses are rare; the dominant problem is partial non-response. Imputation aims to restore the overall structure of a survey dataset by filling in these missing values. It has its own well-defined evaluation criteria and differs fundamentally from prediction. We propose to impute missing survey data through in-context learning (ICL). We systematically evaluate ICL design choices across different missingness mechanisms (MCAR, MAR, MNAR) on 150 opinion variables spanning 15 waves of the American Trends Panel. Compared to well-established statistical methods for data imputation like MICE PMM, our ICL approach consistently reduces absolute error across all missingness mechanisms, with the largest gains under non-random missingness (MNAR). Notably, the best-performing specification (gpt-oss-120b with 100 in-context examples) achieves near-nominal aggregate coverage (approaching the 95% level) with confidence intervals two to five times narrower than MICE PMM. We publish a Python package with an sklearn-like API to enable easy deployment of our method using local and proprietary LLMs.

cs.CL↗

arXiv2025

Learning from Convenience Samples: A Case Study on Fine-Tuning LLMs for Survey Non-response in the German Longitudinal Election Study

Survey researchers face two key challenges: the rising costs of probability samples and missing data (e.g., non-response or attrition), which can undermine inference and increase the use of convenience samples. Recent work explores using large language models (LLMs) to simulate respondents via persona-based prompts, often without labeled data. We study a more practical setting where partial survey responses exist: we fine-tune LLMs on available data to impute self-reported vote choice under both random and systematic nonresponse, using the German Longitudinal Election Study. We compare zero-shot prompting and supervised fine-tuning against tabular classifiers (e.g., CatBoost) and test how different convenience samples (e.g., students) used for fine-tuning affect generalization. Our results show that when data are missing completely at random, fine-tuned LLMs match tabular classifiers but outperform zero-shot approaches. When only biased convenience samples are available, fine-tuning small (3B to 8B) open-source LLMs can recover both individual-level predictions and population-level distributions more accurately than zero-shot and often better than tabular methods. This suggests fine-tuned LLMs offer a promising strategy for researchers working with non-probability samples or systematic missingness, and may enable new survey designs requiring only easily accessible subpopulations.

cs.CY↗

arXiv2025

Computational Reproducibility of R Code Supplements on OSF

Computational reproducibility is fundamental to scientific research, yet many published code supplements lack the necessary documentation to recreate their computational environments. While researchers increasingly share code alongside publications, the actual reproducibility of these materials remains poorly understood. In this work, we assess the computational reproducibility of 296 R projects using the StatCodeSearch dataset. Of these, only 264 were still retrievable, and 98.8% lacked formal dependency descriptions required for successful execution. To address this, we developed an automated pipeline that reconstructs computational environments directly from project source code. Applying this pipeline, we executed the R scripts within custom Docker containers and found that 25.87% completed successfully without error. We conducted a detailed analysis of execution failures, identifying reproducibility barriers such as undeclared dependencies, invalid file paths, and system-level issues. Our findings show that automated dependency inference and containerisation can support scalable verification of computational reproducibility and help identify practical obstacles to code reuse and transparency in scientific research.

cs.CY↗

arXiv2024

Technical Report: Incorporating Blogs in Pollux

This technical report describes the incorporation of political blogs into Pollux, the Specialised Information Service (FID) for Political Science in Germany. Considering the widespread use of political blogs in political science research, we decided to include them in the Pollux search system to enhance the available information infrastructure. We describe the crawling and analyzing of the blogs and the pipeline that integrates them into the Pollux system. To demonstrate the content of the incorporated blogs, we also provide a visualization of the topics covered by the blog posts during the first three months following integration.

cs.DL↗