@misc{PUB-0067,
  title = {{Addressing the Gaps: Recommendations for Supporting the Long Tail of Research Data}},
  author = {Horstmann, W. and Nurnberger, A. and Shearer, K. and Wolski, M.},
  year = {2017},
  doi = {10.15497/RDA00023},
  url = {https://doi.org/10.15497/RDA00023},
  abstract = {Major societal challenges such as health, climate change, energy, food availability, migration
and peace depend on the contributions of a distributed and diverse international network of
researchers and subject experts. The aim of open science is to improve the accessibility of
research outputs, including articles, data and other research objects, so that researchers,
industry and the public can make use of, build on, and ensure the validity of these research
outputs. Among research outputs, research data are often the most diverse - as diverse as the
international network of experts that perform research. Datasets may be small or large, simple
or complex, structured or unstructured. Data may stem from hundreds of different subjects, may
be produced by numerous methodologies, and exist in a plethora of different formats. The
diversity of data is also characterized by a variety of data management practices, of varying
quality and comprehensiveness. Historically, large structured datasets in well-established
disciplines are more likely to adopt unified and standardized formats that are disciplinarily
defined and accepted. Similarly well established disciplines tend to have common and
understood workflows, where as in the long tail of research it is not unusual for researchers
to use a variety of tools and to develop ad-hoc data workflows. Long tail datasets, on the
other hand, which vary radically in source, discipline, size, subject, provenance, funding,
format, longevity, location and complexity, are less likely to adhere to common standards. The
wide distribution and diversity of long-tail data means that ensuring such data is
discoverable and stored in appropriate formats with relevant curation and metadata to
facilitate reuse is challenging, and that these data have received less attention
historically. Furthermore, the terms used to refer to long tail data, e.g. 'small data',
'legacy data' or 'orphan data' have contributed to diminishing the perceived importance of
such data. Considering that a large portion of research datasets (and associated research
funding) are found in the long tail, it is paramount that we address the specific and unique
data management challenges for this data. The risks of neglecting long-tail data are real and
significant. These include both limiting the reproducibility, transparency, and verifiability
of research results, and RDA Long Tail of Research Data Interest Group unnecessary costs
associated with the duplication of research data. Moreover, the potential benefits for reuse
are significantly reduced. The Research Data Alliance (RDA) "Long Tail of Research Data
Interest Group" has been assessing the situation of long tail data over the last three years,
and urges the broader community to consider the risks and opportunities related to long-tail
data. This document provides seven recommendations for a variety of stakeholders, including
governments, funders, research institutions and researchers to help improve the current
approach to managing long tail data. We call on the community to work together to create
necessary and sufficient conditions to ensure we are able to properly steward these valuable
research outputs for future generations of researchers.},
  note = {Horstmann, W., Nurnberger, A., Shearer, K., \& Wolski, M. (2017). Addressing the Gaps: Recommendations for Supporting the Long Tail of Research Data. Research Data Alliance.}
}