A Proposal to Extend and Enrich the Scientific Data Curation of Evaluation Campaigns

◮Using the experimental data, we produce different performance measurements, such as precision and recall, that are standard measures that are used to evaluate the performances of an Information Retrieval System (IRS) for a given experiment. Starting from these performance measurements, we can compute descriptive statistics, such as mean or median, used to summarize the overall performances achieved by an experiment or by a collection of experiments. Finally, we can perform hypothesis tests and other statistical analyses to conduct an in-depth analysis and comparison over a set of experiments.