@inproceedings{msr-2019-swh,
title = {The Software Heritage Graph Dataset: Public software development under one roof},
author = {Antoine Pietri and Diomidis Spinellis and Stefano Zacchiroli},
url = {https://upsilon.cc/~zack/research/publications/msr-2019-swh.pdf},
doi = {10.1109/MSR.2019.00030},
year = {2019},
date = {2019-05-27},
booktitle = {Proceedings of the 16th International Conference on Mining Software Repositories},
pages = {138-142},
publisher = {IEEE Press},
series = {MSR '19},
abstract = {Software Heritage is the largest existing public archive of software source code and accompanying development history: it currently spans more than five billion unique source code files and one billion unique commits, coming from more than 80 million software projects. This paper introduces the Software Heritage graph dataset: a fully-deduplicated Merkle DAG representation of the Software Heritage archive. The dataset links together file content identifiers, source code directories, Version Control System (VCS) commits tracking evolution over time, up to the full states of VCS repositories as observed by Software Heritage during periodic crawls. The dataset's contents come from major development forges (including GitHub and GitLab), FOSS distributions (e.g., Debian), and language-specific package managers (e.g., PyPI). Crawling information is also included, providing timestamps about when and where all archived source code artifacts have been observed in the wild. The Software Heritage graph dataset is available in multiple formats, including downloadable CSV dumps and Apache Parquet files for local use, as well as a public instance on Amazon Athena interactive query service for ready-to-use powerful analytical processing. Source code file contents are cross-referenced at the graph leaves, and can be retrieved through individual requests using the Software Heritage archive API.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{benevol-2018-swh,
title = {Towards Universal Software Evolution Analysis},
author = {Antoine Pietri and Stefano Zacchiroli},
url = {https://upsilon.cc/~zack/research/publications/benevol-2018-swh.pdf},
issn = {1613-0073},
year = {2018},
date = {2018-12-01},
booktitle = {BENEVOL 2018: The 17th Belgium-Netherlands Software Evolution Workshop},
volume = {2361},
pages = {6-10},
series = {CEUR Workshop Proceedings (CEUR-WS)},
abstract = {Software evolution studies have mostly focused on individual software products, generally developed as Free/Open Source Software (FOSS) projects, and more sparingly on software collections like component and package ecosystems. We argue in this paper that the next step in this organic scale expansion is universal software evolution analysis, i.e., the study of software evolution at the scale of the whole body of publicly available software. We consider the case of Software Heritage, the largest existing archive of publicly available software source code artifacts (more than 5 B unique files archived and 1 B commits, coming from more than 80 M software projects). We propose research requirements that would allow to leverage the Software Heritage archive to study universal software evolution. We discuss the challenges that need to be overcome to address such requirements and outline a research roadmap to do so.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@article{cacm-2018-software-heritage,
title = {Building the Universal Archive of Source Code},
author = {Jean-François Abramatic and Roberto Di Cosmo and Stefano Zacchiroli},
editor = {ACM},
url = {https://cacm.acm.org/magazines/2018/10/231366-building-the-universal-archive-of-source-code/fulltext},
doi = {10.1145/3183558},
issn = {0001-0782},
year = {2018},
date = {2018-10-01},
journal = {Communications of the ACM},
volume = {61},
number = {10},
pages = {29-31},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@inproceedings{dicosmo:hal-01865790,
title = {Identifiers for Digital Objects: the Case of Software Source Code Preservation},
author = {Roberto Di Cosmo and Morane Gruenpeter and Stefano Zacchiroli},
url = {https://hal.archives-ouvertes.fr/hal-01865790
https://hal.archives-ouvertes.fr/hal-01865790/file/main.pdf},
doi = {10.17605/OSF.IO/KDE56},
year = {2018},
date = {2018-09-01},
booktitle = {iPRES 2018 - 15th International Conference on Digital Preservation},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}

@misc{barborini:hal-01738741,
title = {The creation of a new type of scientific deposit: Software},
author = {Yannick Barborini and Roberto Di Cosmo and Antoine R. Dumont and Morane Gruenpeter and Bruno P. Marmol and Alain Monteil and Jozefina Sadowska and Stefano Zacchiroli},
url = {https://hal.inria.fr/hal-01738741
https://hal.inria.fr/hal-01738741/file/2018-03-21-RDA-Poster.pdf},
year = {2018},
date = {2018-03-21},
howpublished = {RDA Eleventh Plenary Meeting, Berlin, Germany},
note = {poster},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}

@misc{barborini:hal-01688726,
title = {La création du nouveau type de dépôt scientifique - Le logiciel},
author = {Yannick Barborini and Roberto Di Cosmo and Antoine R. Dumont and Morane Gruenpeter and Bruno P. Marmol and Alain Monteil and Jozefina Sadowska and Stefano Zacchiroli},
url = {https://hal.inria.fr/hal-01688726
https://hal.inria.fr/hal-01688726/file/2018-01-22-JSO2018-Poster.pdf},
year = {2018},
date = {2018-01-22},
howpublished = {JSO 2018 - 7es journées Science Ouverte Couperin : 100 % open access : initiatives pour une transition réussie},
note = {poster},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}

@inproceedings{dicosmo:hal-01590958,
title = {Software Heritage: Why and How to Preserve Software Source Code},
author = {Roberto Di Cosmo and Stefano Zacchiroli},
url = {https://hal.archives-ouvertes.fr/hal-01590958
https://hal.archives-ouvertes.fr/hal-01590958/file/ipres-2017-software-heritage.pdf},
year = {2017},
date = {2017-09-25},
booktitle = {iPRES 2017: 14th International Conference on Digital Preservation},
address = {Kyoto, Japan},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}