references.bib

@book{schweik2012internet,
  title={Internet success: a study of open-source software commons},
  author={Schweik, Charles M and English, Robert C},
  year={2012},
  publisher={MIT Press},
  ISBN={9780262017251}
}


@misc{tennant_et_al_2020,
 title={A tale of two 'opens': intersections between Free and Open Source Software and Open Scholarship},
 url={https://osf.io/preprints/socarxiv/2kxq8},
 DOI={10.31235/osf.io/2kxq8},
 publisher={SocArXiv},
 author={Tennant, Jonathan and Agarwal, Ritwik and Baždarić, Ksenija and Brassard, David and Crick, Tom and Dunleavy, Daniel J. and Evans, Thomas R. and
 Gardner, Nicholas and Gonzalez-Marquez, Monica and Graziotin, Daniel and others},
 year={2020},
 month={Mar}
}


@article{10.1371/journal.pone.0231939,
    author = {Huppenkothen, Daniela and McFee, Brian and Norén, Laura},
    journal = {PLOS ONE},
    publisher = {Public Library of Science},
    title = {Entrofy your cohort: A transparent method for diverse cohort selection},
    year = {2020},
    month = {07},
    volume = {15},
    url = {https://doi.org/10.1371/journal.pone.0231939},
    pages = {1-35},
    abstract = {Selecting a cohort from a set of candidates is a common task within and beyond academia. Admitting students, awarding grants, and choosing speakers for a conference are situations where human biases may affect the selection of any particular candidate, and, thereby the composition of the final cohort. In this paper, we propose a new algorithm, entrofy, designed to be part of a human-in-the-loop decision making strategy aimed at making cohort selection as just, transparent, and accountable as possible. We suggest embedding entrofy in a two-step selection procedure. During a merit review, the committee selects all applicants, submissions, or other entities that meet their merit-based criteria. This often yields a cohort larger than the admissible number. In the second stage, the target cohort can be chosen from this meritorious pool via a new algorithm and software tool called entrofy. entrofy optimizes differences across an assignable set of categories selected by the human committee. Criteria could include academic discipline, home country, experience with certain technologies, or other quantifiable characteristics. The entrofy algorithm then yields the approximation of pre-defined target proportions for each category by solving the tie-breaking problem with provable performance guarantees. We show how entrofy selects cohorts according to pre-determined characteristics in simulated sets of applications and demonstrate its use in a case study of Astro Hack Week. This two stage candidate and cohort selection process allows human judgment and debate to guide the assessment of candidates’ merit in step 1. Then the human committee defines relevant diversity criteria which will be used as computational parameters in entrofy. Once the parameters are defined, the set of candidates who meet the minimum threshold for merit are passed through the entrofy cohort selection procedure in step 2 which yields a cohort of a composition as close as possible to the computational parameters defined by the committee. This process has the benefit of separating the meritorious assessment of candidates from certain elements of their diversity and from some considerations around cohort composition. It also increases the transparency and auditability of the process, which enables, but does not guarantee, fairness. Splitting merit and diversity considerations into their own assessment stages makes it easier to explain why a given candidate was selected or rejected, though it does not eliminate the possibility of objectionable bias.},
    number = {7},
    doi = {10.1371/journal.pone.0231939}
}

@Article{10.12688/f1000research.16231.1,
AUTHOR = {Sufi, Shoaib and Jay, Caroline},
TITLE = {Raising the status of software in research: A survey-based evaluation of the Software Sustainability Institute Fellowship Programme [version 1; peer review: 3 approved with reservations]
},
JOURNAL = {F1000Research},
VOLUME = {7},
YEAR = {2018},
NUMBER = {1599},
DOI = {10.12688/f1000research.16231.1}
}


@book{df80bc12-en,
   author = {{Organisation for Economic Cooperation and Development}},
   title = {OECD Skills Outlook 2019},
   year = 2019,
   pages = 285,
   doi = {10.1787/df80bc12-en},
}

@article{barone2017unmet,
  title={Unmet needs for analyzing biological big data: A survey of 704 {NSF} principal investigators},
  author={Barone, Lindsay and Williams, Jason and Micklos, David},
  journal={PLoS computational biology},
  volume={13},
  number={10},
  year={2017},
  publisher={Public Library of Science},
  doi={10.1371/journal.pcbi.1005755},
}

@article{carver2018conceptualization,
  title={Conceptualization of a {US} research software sustainability institute ({URSSI})},
  author={Carver, Jeffrey C. and Gesing, Sandra and Katz, Daniel S. and Ram, Karthik and Weber, Nicholas},
  journal={Computing in Science \& Engineering},
  volume={20},
  number={3},
  pages={4--9},
  year={2018},
  publisher={IEEE Computer Society},
  doi={10.1109/MCSE.2018.03221924},
}

@techreport{collberg2015repeatability,
  title={Repeatability and benefaction in computer systems research},
  author={Collberg, Christian and Proebsting, Todd and Warren, Alex M},
  type={Department of Computer Science, University of Arizona TR},
  number={14-04},
  year={2014},
  url={http://repeatability.cs.arizona.edu/v2/RepeatabilityTR.pdf},
}

@techreport{collberg2014measuring,
  title={Measuring reproducibility in computer systems research},
  author={Collberg, Christian and Proebsting, Todd and Moraila, Gina and Shankaran, Akash and Shi, Zuoming and Warren, Alex M},
  type={Department of Computer Science, University of Arizona TR},
  number={13-03},
  year={2013},
  url={https://www.cs.arizona.edu/sites/default/files/TR13-03.pdf},
}

@misc{hettrick2014,
  title={UK Research Software Survey 2014},
  DOI={10.5281/zenodo.14809},
  publisher={Zenodo},
  author={Hettrick, Simon and Antonioletti, Mario and Carr, Les and Chue Hong, Neil and Crouch, Stephen and De Roure, David and Emsley, Iain and Goble, Carole and Hay, Alexander and Inupakutika, Devasena and et al.},
  year={2014},
  month={Dec},
}

@misc{RSEHettrick,
  author={Simon Hettrick},
  title={A brief history of {R}esearch {S}oftware {E}ngineers in the {UK}},
  url={http://bit.ly/RSEHettrick},
  year={2016},
}

@misc{simon_hettrick_2018_1183562,
  author       = {Simon Hettrick},
  title        = {{softwaresaved/software\_in\_research\_survey\_2014:
                   Software in research survey}},
  month        = feb,
  year         = 2018,
  publisher    = {Zenodo},
  version      = {1.0},
  doi          = {10.5281/zenodo.1183562},
}

@misc{Hettrick-blog,
  title={It's impossible to conduct research without software, say 7 out of 10 UK researchers},
  author={Simon Hettrick},
  url={https://www.software.ac.uk/blog/2014-12-04-its-impossible-conduct-research-without-software-say-7-out-10-uk-researchers},
  year={2014},
}

@article{howison2016software,
  title={Software in the scientific literature: Problems with seeing, finding, and using software mentioned in the biology literature},
  author={Howison, James and Bullard, Julia},
  journal={Journal of the Association for Information Science and Technology},
  volume={67},
  number={9},
  pages={2137--2155},
  year={2016},
  publisher={Wiley Online Library},
  doi={10.1002/asi.23538},
}

@article {Huppenkothen8872,
	author = {Huppenkothen, Daniela and Arendt, Anthony and Hogg, David W. and Ram, Karthik and VanderPlas, Jacob T. and Rokem, Ariel},
	title = {Hack weeks as a model for data science education and collaboration},
	volume = {115},
	number = {36},
	pages = {8872--8877},
	year = {2018},
	doi = {10.1073/pnas.1717196115},
	publisher = {National Academy of Sciences},
	issn = {0027-8424},
	URL = {https://www.pnas.org/content/115/36/8872},
	journal = {Proceedings of the National Academy of Sciences}
}

@misc{nangia_katz_2017,
title= {Track 1 Paper: Surveying the {U.S.} National Postdoctoral Association Regarding Software Use and Training in Research},
DOI={10.6084/m9.figshare.5328442.v3},
publisher={figshare},
author={Nangia, Udit and Katz, Daniel S.},
year={2017},
month={Aug}
}

@INPROCEEDINGS{Pinto2018,
author={Gustavo Pinto and Igor Wiese and Luiz Felipe Dias},
booktitle={25th International Conference on Software Analysis, Evolution and Reengineering ({SANER})},
title={How do scientists develop scientific software? An external replication},
year={2018},
pages={582-591},
doi={10.1109/SANER.2018.8330263},
month={March},
}

@article{price2018astropy,
title={The {A}stropy Project: Building an inclusive, open-science project and status of the v2.0 core package},
author={Price-Whelan, A. M. and Sipőcz, B. M. and Günther, H. M. and Lim, P. L. and Crawford, S. M. and Conseil, S. and Shupe, D. L. and Craig, M. W. and Dencheva, N. and others},
journal={arXiv preprint arXiv:1801.02634},
doi={10.3847/1538-3881/aabc4f},
year={2018},
}

@article{robitaille2013astropy,
title={Astropy: A community {P}ython package for astronomy},
author={Robitaille, Thomas P. and Tollerud, Erik J. and Greenfield, Perry and Droettboom, Michael and Bray, Erik and Aldcroft, Tom and Davis, Matt and Ginsburg, Adam and Price-Whelan, Adrian M. and Kerzendorf, Wolfgang E and others},
journal={Astronomy \& Astrophysics},
volume={558},
pages={A33},
year={2013},
publisher={EDP Sciences},
doi={10.1051/0004-6361/201322068},
}

@incollection{rohl2004protein,
title={Protein structure prediction using {R}osetta},
author={Rohl, Carol A. and Strauss, Charlie E. M. and Misura, Kira M. S. and Baker, David},
booktitle={Methods in Enzymology},
volume={383},
pages={66--93},
year={2004},
publisher={Elsevier},
doi={10.1016/S0076-6879(04)83004-0},
}

@article{salmena2011cerna,
title={A {ceRNA} hypothesis: the {R}osetta Stone of a hidden {RNA} language?},
author={Salmena, Leonardo and Poliseno, Laura and Tay, Yvonne and Kats, Lev and Pandolfi, Pier Paolo},
journal={Cell},
volume={146},
number={3},
pages={353--358},
year={2011},
publisher={Elsevier},
doi={10.1016/j.cell.2011.07.014}
}

@misc{softwarecarpentryhistory,
title={The History of Software Carpentry},
url={https://software-carpentry.org/scf/history/},
author={{Software Carpentry}},
year={n. d.}
}

@article{wilsong2016,
AUTHOR = {Wilson, Greg},
TITLE = {Software Carpentry: lessons learned [version 2; peer review: 3 approved]},
JOURNAL = {F1000Research},
VOLUME = {3},
YEAR = {2016},
NUMBER = {62},
DOI = {10.12688/f1000research.3-62.v2},
}

@article{moher2018assessing,
title={Assessing scientists for hiring, promotion, and tenure},
author={Moher, David and Naudet, Florian and Cristea, Ioana A. and Miedema, Frank and Ioannidis, John P. A. and Goodman, Steven N.},
journal={PLoS biology},
volume={16},
number={3},
pages={e2004089},
year={2018},
publisher={Public Library of Science},
doi={10.1371/journal.pbio.2004089}
}

@article{park2019research,
  title={Research software citation in the Data Citation Index: Current practices and implications for research software sharing and reuse},
  author={Park, Hyoungjoo and Wolfram, Dietmar},
  journal={Journal of Informetrics},
  volume={13},
  number={2},
  pages={574--582},
  year={2019},
  publisher={Elsevier},
  doi={10.1016/j.joi.2019.03.005}
}

@article{hwang2017software,
  title={Software and the scientist: Coding and citation practices in geodynamics},
  author={Hwang, Lorraine and Fish, Allison and Soito, Laura and Smith, MacKenzie and Kellogg, Louise H.},
  journal={Earth and Space Science},
  volume={4},
  number={11},
  pages={670--680},
  year={2017},
  publisher={Wiley Online Library},
  doi={10.1002/2016EA000225}
}

@article{hsu2019comparing,
  title={Comparing the Use of Research Resource Identifiers and Natural Language Processing for Citation of Databases, Software and Other Digital Artifacts},
  author={Hsu, Chun-Nan and Bandrowski, Anita and Gillespie, Thomas H. and Udell, Jon and Lin, Ko-Wei and Burak, Ibrahim and Grethe, Jeffrey S. and Martone, Maryann},
  journal={Computing in Science \& Engineering},
  year={2019},
  publisher={IEEE},
  doi={10.1109/MCSE.2019.2952838}
}

@article{siepel2019challenges,
title={Challenges in funding and developing genomic software: roots and remedies},
author={Siepel, Adam},
journal={Genome biology},
volume={20},
number={1},
pages={147},
year={2019},
publisher={Springer},
doi={10.1186/s13059-019-1763-7}
}

@inproceedings{broman2017recommendations,
title={Recommendations to funding agencies for supporting reproducible research},
author={Broman, Karl and Cetinkaya-Rundel, Mine and Nussbaum, Amy and Paciorek, Christopher and Peng, Roger and Turek, Daniel and Wickham, Hadley},
booktitle={American Statistical Association},
volume={2},
year={2017},
url={https://www.amstat.org/asa/files/pdfs/pol-reproducibleresearchrecommendations.pdf}
}

@article{howison2015sustaining,
title={Sustaining scientific infrastructures: transitioning from grants to peer production (work-in-progress)},
author={Howison, James},
journal={iConference 2015 Proceedings},
year={2015},
publisher={iSchools},
url={http://hdl.handle.net/2142/73439}
}

@article{geiger2018types,
title={The types, roles, and practices of documentation in data analytics open source software libraries},
author={Geiger, R. Stuart and Varoquaux, Nelle and Mazel-Cabasse, Charlotte and Holdgraf, Chris},
journal={Computer Supported Cooperative Work (CSCW)},
volume={27},
number={3-6},
pages={767--802},
year={2018},
publisher={Springer},
doi={10.1007/s10606-018-9333-1}
}

@article{bourque2004swebok,
title={Guide to the Software Engineering Body of Knowledge (SWEBOK Guide)},
author={Bourque, Pierre and Fairley, R.},
journal={IEEE Computer Society},
year={2004},
url={http://www.swebok.org},
}

@book{eghbal2016roads,
title={Roads and bridges: The unseen labor behind our digital infrastructure},
author={Eghbal, Nadia},
year={2016},
publisher={Ford Foundation},
url={https://www.fordfoundation.org/work/learning/research-reports/roads-and-bridges-the-unseen-labor-behind-our-digital-infrastructure/}
}

@inproceedings{coelho2017modern,
title={Why modern open source projects fail},
author={Coelho, Jailton and Valente, Marco Tulio},
booktitle={Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering},
pages={186--196},
year={2017},
doi={10.1145/3106237.3106246}
}

@inproceedings{almeida2017software,
title={Do software developers understand open source licenses?},
author={Almeida, Daniel A. and Murphy, Gail C. and Wilson, Greg and Hoye, Mike},
booktitle={2017 IEEE/ACM 25th International Conference on Program Comprehension (ICPC)},
pages={1--11},
year={2017},
organization={IEEE},
doi={10.1109/ICPC.2017.7}
}

@incollection{stewart2016studies,
  title={Studies of Success in Open Source Source Software Projects},
  author={Stewart, Katherine},
  booktitle={Successful {OSS} Project Design and Implementation},
  pages={145--162},
  year={2016},
  publisher={Routledge},
  isbn={0566087952},
  doi={10.4324/9781315611235}
}

@article{o2007governance,
  title={The governance of open source initiatives: what does it mean to be community managed?},
  author={O’Mahony, Siobh{\'a}n},
  journal={Journal of Management \& Governance},
  volume={11},
  number={2},
  pages={139--150},
  year={2007},
  publisher={Springer},
  doi={10.1007/s10997-007-9024-7}
}

@article{shaikh2017governing,
  title={Governing open source software through coordination processes},
  author={Shaikh, Maha and Henfridsson, Ola},
  journal={Information and Organization},
  volume={27},
  number={2},
  pages={116--135},
  year={2017},
  publisher={Elsevier},
  doi={10.1016/j.infoandorg.2017.04.001}
}

@inproceedings{aversano2017evaluating,
  title={Evaluating the Quality of the Documentation of Open Source Software.},
  author={Aversano, Lerina and Guardabascio, Daniela and Tortorella, Maria},
  booktitle={ENASE},
  pages={308--313},
  year={2017},
  doi={10.5220/0006369403080313}
}

@article{ram2018community,
  title={A Community of Practice Around Peer Review for Long-Term Research Software Sustainability},
  author={Ram, Karthik and Boettiger, Carl and Chamberlain, Scott and Ross, Noam and Salmon, Ma{\"e}lle and Butland, Stefanie},
  journal={Computing in Science \& Engineering},
  volume={21},
  number={2},
  pages={59--65},
  year={2018},
  publisher={IEEE},
  doi={10.1109/MCSE.2018.2882753}
}

@techreport{NSF2017,
  author = {{National Science Foundation}},
  title = {Women, Minorities, and Persons with Disabilities in Science and Engineering},
  booktitle = {NSF 17-310},
  year={2017},
  url={https://www.nsf.gov/statistics/2017/nsf17310/},
}

@inproceedings{Vasilescu2012,
  author={Bogdan Vasilescu and Andrea Capiluppi and Alexander Serebrenik},
  booktitle={2012 International Conference on Social Informatics},
  title={Gender, Representation and Online Participation: A Quantitative Study of {StackOverflow}},
  year={2012},
  volume={},
  number={},
  pages={332--338},
  ISSN={},
  month={Dec},
  doi={10.1109/SocialInformatics.2012.81},
}

@inproceedings{Vasilescu2015,
  author = {Vasilescu, Bogdan and Posnett, Daryl and Ray, Baishakhi and van den Brand, Mark G. J. and Serebrenik, Alexander and Devanbu, Premkumar and Filkov, Vladimir},
  title = {Gender and Tenure Diversity in {GitHub} Teams},
  booktitle = {33rd Annual {ACM} Conference on Human Factors in Computing Systems},
  series = {CHI '15},
  year = {2015},
  isbn = {978-1-4503-3145-6},
  pages = {3789--3798},
  numpages = {10},
  doi={10.1145/2702123.2702549}
}

@article{Daniel2013,
  author = {Sherae Daniel and Ritu Agarwal and Katherine J. Stewart},
  title = {The Effects of Diversity in Global, Distributed Collectives: A Study of Open Source Project Success},
  journal = {Information Systems Research},
  volume = {24},
  number = {2},
  pages = {312--333},
  year = {2013},
  doi={10.1287/isre.1120.0435},
}

@article{Nafus2012,
  author = {Dawn Nafus},
  title ={'Patches don't have gender': What is not open in open source software},
  journal = {New Media \& Society},
  volume = {14},
  number = {4},
  pages = {669--683},
  year = {2012},
  doi={10.1177/1461444811422887},
}

@article{Powell2010,
  title={Gender differences within the open source community: An exploratory study},
  author={Powell, Whitney E. and Hunsinger, D. Scott and Medlin, B. Dawn},
  journal={Journal of Information Technology},
  volume={21},
  number={4},
  pages={29--37},
  year={2010},
  url={http://jitm.ubalt.edu/XXI-4/article3.pdf},
}

@article{Reagle2012,
  title={``Free as in sexist?'' Free culture and the gender gap},
  author={Reagle, Joseph},
  journal={first monday},
  volume={18},
  number={1},
  year={2012},
  doi={10.5210/fm.v18i1.4291},
}

@inproceedings{Lee2019,
  author={Amanda Lee and Jeffrey C. Carver},
  booktitle={{IEEE/ACM} 41st International Conference on Software Engineering (ICSE)},
  title={FLOSS Participants' Perceptions About Gender and Inclusiveness: A Survey},
  year={2019},
  pages={677--687},
  doi={10.1109/ICSE.2019.00077},
}

@software{rse-survey,
  author       = {Olivier Philippe and
                  Martin Hammitzsch and
                  Stephan Janosch and
                  Anelda van der Walt and
                  Ben van Werkhoven and
                  Simon Hettrick and
                  Daniel S. Katz and
                  Katrin Leinweber and
                  Sandra Gesing and
                  Stephan Druskat and
                  Scott Henwood and
                  Nicholas R. May and
                  Nooriyah P. Lohani and
                  Manodeep Sinha},
  title        = {{softwaresaved/international-survey: Public release
                   for 2018 results}},
  month        = mar,
  year         = 2019,
  publisher    = {Zenodo},
  version      = {2018-v.1.0.2},
  doi          = {10.5281/zenodo.2585783},
  url          = {https://github.com/softwaresaved/international-survey}
}

@techreport{OSPP_report,
title={Progress on open science: Towards a shared research knowledge system: Final report of the {O}pen {S}cience {P}olicy {P}latform},
author={Eva Mendez and Rebecca Lawrence and Catriona J. MacCallum and Eva Moar and {Open Science Policy Platform members}},
doi={10.2777/00139},
institution={European Commission},
year=2020,
}

@misc{RDA-covid-recs-final,
  title={Final release: COVID-19 guidelines},
  doi={10.15497/RDA00052},
  publisher={RDA},
  author={{Research Data Alliance}},
  year=2020,
  month=jun,
}

@software{olivier_philippe_2019_2585783,
  author       = {Olivier Philippe and
                  Martin Hammitzsch and
                  Stephan Janosch and
                  Anelda van der Walt and
                  Ben van Werkhoven and
                  Simon Hettrick and
                  Daniel S. Katz and
                  Katrin Leinweber and
                  Sandra Gesing and
                  Stephan Druskat and
                  Scott Henwood and
                  Nicholas R. May and
                  Nooriyah P. Lohani and
                  Manodeep Sinha},
  title        = {{softwaresaved/international-survey: Public release
                   for 2018 results}},
  month        = mar,
  year         = 2019,
  publisher    = {Zenodo},
  version      = {2018-v.1.0.2},
  doi          = {10.5281/zenodo.2585783},
  url          = {https://doi.org/10.5281/zenodo.2585783}
}