How to Measure the Reproducibility of System-oriented IR Experiments

TL;DR

This paper proposes methods to quantify the reproducibility of system-oriented IR experiments and introduces a dataset to validate these measures, addressing a key gap in reproducibility assessment.

Contribution

It compares various measures for assessing IR experiment reproducibility and creates a dataset for validation and future research.

Findings

Different measures operate at various granularity levels.

The dataset enables validation of reproducibility measures.

The methods help quantify the extent of experiment replication.

Abstract

Replicability and reproducibility of experimental results are primary concerns in all the areas of science and IR is not an exception. Besides the problem of moving the field towards more reproducible experimental practices and protocols, we also face a severe methodological issue: we do not have any means to assess when reproduced is reproduced. Moreover, we lack any reproducibility-oriented dataset, which would allow us to develop such methods. To address these issues, we compare several measures to objectively quantify to what extent we have replicated or reproduced a system-oriented IR experiment. These measures operate at different levels of granularity, from the fine-grained comparison of ranked lists, to the more general comparison of the obtained effects and significant differences. Moreover, we also develop a reproducibility-oriented dataset, which allows us to validate our measures and which can also be used to develop future measures.