@inproceedings{desmazieres:hal-04924849,

title = {50 Years of Programming Language Evolution through the Software Heritage looking glass},

author = {Adèle Desmazières and Roberto Di Cosmo and Valentin Lorentz},

editor = {IEEE},

url = {https://hal.science/hal-04924849},

year  = {2025},

date = {2025-04-01},

booktitle = {Mining Software Repositories},

address = {Ottawa (Canada), Canada},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{acm-rep-2024-guix-swh,

title = {Source Code Archiving to the Rescue of Reproducible Deployment},

author = {Ludovic Courtès and Timothy Sample and Simon Tournier and Stefano Zacchiroli},

doi = {10.1145/3641525.3663622},

year  = {2024},

date = {2024-07-11},

urldate = {2024-01-01},

booktitle = {2024 ACM Conference on Reproducibility and Replicability},

pages = {10 pages},

publisher = {ACM},

abstract = {The ability to verify research results and to experiment with methodologies are core tenets of science. As research results are increasingly the outcome of computational processes, software plays a central role. GNU Guix is a software deployment tool that supports reproducible software deployment, making it a foundation for computational research workflows. To achieve reproducibility, we must first ensure the source code of software packages Guix deploys remains available. We describe our work connecting Guix with Software Heritage, the universal source code archive, making Guix the first free soft- ware distribution and tool backed by a stable archive. Our contribution is twofold: we explain the rationale and present the design and implementation we came up with; second, we report on the archival coverage for package source code with data collected over five years and discuss remaining challenges.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{www-2024-webgraph-rs,

title = {WebGraph: The Next Generation (Is in Rust)},

author = {Tommaso Fontana and Sebastiano Vigna and Stefano Zacchiroli},

doi = {10.1145/3589335.3651581},

year  = {2024},

date = {2024-05-13},

booktitle = {Companion Proceedings of the ACM Web Conference 2024 (WWW '24 Companion)},

pages = {686-689},

publisher = {ACM},

abstract = {We report the results of a yearlong effort to port the WebGraph framework from Java to Rust. For two decades WebGraph has been instrumental in the analysis and distribution of large graphs for the research community of TheWebConf, but the intrinsic limitations of the Java Virtual Machine had become a bottleneck for very large use cases, such as the Software Heritage Merkle graph with its half a trillion arcs. As part of this clean-slate implementation of WebGraph in Rust, we developed a few ancillary projects bringing to the Rust ecosystem some missing features of independent interest, such as easy, consistent and zero-cost memory mapping of data structures. WebGraph in Rust offers impressive performance improvements over the previous implementation, enabling open-source graph analytics on very large datasets on top of a modern system programming language.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{acm-rep-2023-reproducible-datasets,

title = {Fingerprinting and Building Large Reproducible Datasets},

author = {Romain Lefeuvre and Jessie Galasso and Benoit Combemale and Houari Sahraoui and Stefano Zacchiroli},

doi = {10.1145/3589806.3600043},

year  = {2023},

date = {2023-01-01},

booktitle = {2023 ACM Conference on Reproducibility and Replicability},

pages = {27-36},

publisher = {ACM},

abstract = {Obtaining a relevant dataset is central to conducting empirical studies in software engineering. However, in the context of mining software repositories, the lack of appropriate tooling for large scale mining tasks hinders the creation of new datasets. Moreover, limitations related to data sources that change over time (e.g., code bases) and the lack of documentation of extraction processes make it difficult to reproduce datasets over time. This threatens the quality and reproducibility of empirical studies. In this paper, we propose a tool-supported approach facilitating the creation of large tailored datasets while ensuring their reproducibility. We leveraged all the sources feeding the Software Heritage append-only archive which are accessible through a unified programming interface to outline a reproducible and generic extraction process. We propose a way to define a unique fingerprint to characterize a dataset which, when provided to the extraction process, ensures that the same dataset will be extracted. We demonstrate the feasibility of our approach by implementing a prototype. We show how it can help reduce the limitations researchers face when creating or reproducing datasets.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{icse-seis-2022-gender,

title = {Worldwide Gender Differences in Public Code Contributions (and How They Have Been Affected by the COVID-19 Pandemic)},

author = {Davide Rossi and Stefano Zacchiroli},

url = {https://www.softwareheritage.org/wp-content/uploads/2022/12/icse-seis-2022-gender.pdf},

doi = {10.1109/ICSE-SEIS55304.2022.9794118},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {44th International Conference on Software Engineering (ICSE 2022) - Software Engineering in Society (SEIS) Track},

pages = {172-183},

publisher = {ACM},

abstract = {Gender imbalance is a well-known phenomenon observed throughout sciences which is particularly severe in software development and Free/Open Source Software communities. Little is know yet about the geography of this phenomenon in particular when considering large scales for both its time and space dimensions. We contribute to fill this gap with a longitudinal study of the population of contributors to publicly available software source code. We analyze the development history of 160 million software projects for a total of 2.2 billion commits contributed by 43 million distinct authors over a period of 50 years. We classify author names by gender using name frequencies and author geographical locations using heuristics based on email addresses and time zones. We study the evolution over time of contributions to public code by gender and by world region. For the world overall, we confirm previous findings about the low but steadily increasing ratio of contributions by female authors. When breaking down by world regions we find that the long-term growth of female participation is a world-wide phenomenon. We also observe a decrease in the ratio of female participation during the COVID-19 pandemic, suggesting that women’s ability to contribute to public code has been more hindered than that of men.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{msr-2022-foss-licenses,

title = {A Large-scale Dataset of (Open Source) License Text Variants},

author = {Stefano Zacchiroli},

url = {https://www.softwareheritage.org/wp-content/uploads/2022/12/msr-2022-foss-licenses.pdf},

doi = {10.1145/3524842.3528491},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {The 2022 Mining Software Repositories Conference (MSR 2022)},

pages = {757-761},

publisher = {ACM},

abstract = {We introduce a large-scale dataset of the complete texts of free/open source software (FOSS) license variants. To assemble it we have collected from the Software Heritage archive—the largest publicly available archive of FOSS source code with accompanying development history—all versions of files whose names are commonly used to convey licensing terms to software users and developers. The dataset consists of 6.5 million unique license files that can be used to conduct empirical studies on open source licensing, training of automated license classifiers, natural language processing (NLP) analyses of legal texts, as well as historical and phylogenetic studies on FOSS licensing. Additional metadata about shipped license files are also provided, making the dataset ready to use in various contexts; they include: file length measures, detected MIME type, detected SPDX license (using ScanCode), example origin (e.g., GitHub repository), oldest public commit in which the license appeared. The dataset is released as open data as an archive file containing all deduplicated license files, plus several portable CSV files for metadata, referencing files via cryptographic checksums.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{msr-2022-foss-geography,

title = {Geographic Diversity in Public Code Contributions: An Exploratory Large-Scale Study Over 50 Years},

author = {Davide Rossi and Stefano Zacchiroli},

url = {https://www.softwareheritage.org/wp-content/uploads/2022/12/msr-2022-foss-geography.pdf},

doi = {10.1145/3524842.3528471},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {The 2022 Mining Software Repositories Conference (MSR 2022)},

pages = {80-85},

publisher = {ACM},

abstract = {We conduct an exploratory, large-scale, longitudinal study of 50 years of commits to publicly available version control system repositories, in order to characterize the geographic diversity of contributors to public code and its evolution over time. We analyze in total 2.2 billion commits collected by Software Heritage from 160 million projects and authored by 43 million authors during the 1971–2021 time period. We geolocate developers to 12 world regions derived from the United Nation geoscheme, using as signals email top-level domains, author names compared with names distributions around the world, and UTC offsets mined from commit metadata. We find evidence of the early dominance of North America in open source software, later joined by Europe. After that period, the geographic diversity in public code has been constantly increasing. We also identify relevant historical shifts related to the UNIX wars, the increase of coding literacy in Central and South Asia, and broader phenomena like colonialism and people movement across countries (immigration/emigration).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{oss-2022-swh-scanner,

title = {Efficient Prior Publication Identification for Open Source Code},

author = {Daniele Serafini and Stefano Zacchiroli},

url = {https://www.softwareheritage.org/wp-content/uploads/2022/12/oss-2022-swh-scanner.pdf},

doi = {10.1145/3555051.3555068},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {18th International Conference on Open Source Systems (OSS 2022)},

publisher = {ACM},

abstract = {Free/Open Source Software (FOSS) enables large-scale reuse of preexisting software components. The main drawback is increased complexity in software supply chain management. A common approach to tame such complexity is automated open source compliance, which consists in automating the verification of adherence to various open source management best practices about license obligation fulfillment, vulnerability tracking, software composition analysis, and nearby concerns. We consider the problem of auditing a source code base to determine which of its parts have been published before, which is an important building block of automated open source compliance toolchains. Indeed, if source code allegedly developed in house is recognized as having been previously published elsewhere, alerts should be raised to investigate where it comes from and whether this entails that additional obligations shall be fulfilled before product shipment. We propose an efficient approach for prior publication identification that relies on a knowledge base of known source code artifacts linked together in a global Merkle direct acyclic graph and a dedicated discovery protocol. We introduce swh-scanner, a source code scanner that realizes the proposed approach in practice using as knowledge base Software Heritage, the largest public archive of source code artifacts. We validate experimentally the proposed approach, showing its efficiency in both abstract (number of queries) and concrete terms (wall-clock time), performing benchmarks on 16'845 real-world public code bases of various sizes, from small to very large.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{dicosmo_tpdl_2022,

title = {Should We Preserve the World's Software History, And Can We?},

author = {Roberto Di Cosmo},

editor = {Gianmaria Silvello and Óscar Corcho and Paolo Manghi and Giorgio Maria Di Nunzio and Koraljka Golub and Nicola Ferro and Antonella Poggi},

url = {http://www.dicosmo.org/Articles/2022-TPDL.pdf},

doi = {10.1007/978-3-031-16802-4-1},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Linking Theory and Practice of Digital Libraries - 26th International 

 Conference on Theory and Practice of Digital Libraries, TPDL 2022, 

 Padua, Italy, September 20-23, 2022, Proceedings},

volume = {13541},

pages = {3--7},

publisher = {Springer},

series = {Lecture Notes in Computer Science},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{osec_2022_en,

title = {Building the software pillar of Open Science},

author = {Roberto Di Cosmo},

url = {http://www.dicosmo.org/Articles/2022-osec-en.pdf},

doi = {10.4000/books.oep.15829},

isbn = {9791036545627},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Open Science European Conferencem (OSEC 2022)},

pages = {183--193},

publisher = {OpenEdition Press},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bussi:hal-03375572,

title = {Preserving landmark legacy software with the Software Heritage Acquisition Process},

author = {Laura Bussi and Roberto Di Cosmo and Carlo Montangero and Guido Scatena},

url = {https://hal.archives-ouvertes.fr/hal-03375572},

year  = {2021},

date = {2021-10-01},

booktitle = {iPres2021 - 17th International Conference on Digital Preservation},

address = {Beijing, China},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{swh-fuse-icse2021,

title = {The Software Heritage Filesystem (SwhFS): Integrating Source Code Archival with Development},

author = {Thibault Allançon and Antoine Pietri and Stefano Zacchiroli},

url = {https://arxiv.org/abs/2102.06390 

https://www.softwareheritage.org/wp-content/uploads/2021/03/swh-fuse-icse2021.pdf},

doi = {10.1109/ICSE-Companion52605.2021.00032},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {ICSE 2021: The 43rd International Conference on Software Engineering},

pages = {45-48},

publisher = {IEEE},

abstract = {We introduce the Software Heritage filesystem (SwhFS), a user-space filesystem that integrates large-scale open source software archival with development workflows. SwhFS provides a POSIX filesystem view of Software Heritage, the largest public archive of software source code and version control system (VCS) development history. Using SwhFS, developers can quickly “checkout” any of the 2 billion commits archived by Software Heritage, even after they disappear from their previous known location and without incurring the performance cost of repository cloning. SwhFS works across unrelated repositories and different VCS technologies. Other source code artifacts archived by Software Heritage—individual source code files and trees, releases, and branches—can also be accessed using common programming tools and custom scripts, as if they were locally available. A screencast of SwhFS is available online at dx.doi.org/10.5281/zenodo.4531411.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{DBLP:conf/icms/Cosmo20,

title = {Archiving and Referencing Source Code with Software Heritage},

author = {Roberto Di Cosmo},

doi = {10.1007/978-3-030-52200-1_36},

isbn = {978-3-030-52200-1},

year  = {2020},

date = {2020-07-15},

booktitle = {ICMS},

volume = {12097},

pages = {362--373},

publisher = {Springer},

series = {Lecture Notes in Computer Science},

abstract = {Software, and software source code in particular, is widely used in modern research. It must be properly archived, referenced, described and cited in order to build a stable and long lasting corpus of scientific knowledge. In this article we show how the Software Heritage universal source code archive provides a means to fully address the first two concerns, by archiving seamlessly all publicly available software source code, and by providing intrinsic persistent identifiers that allow to reference it at various granularities in a way that is at the same time convenient and effective. 

 

We call upon the research community to adopt widely this approach.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{msr-2020-challenge,

title = {The Software Heritage Graph Dataset: Large-scale Analysis of Public Software Development History},

author = {Antoine Pietri and Diomidis Spinellis and Stefano Zacchiroli},

url = {https://arxiv.org/abs/2011.07824 

https://www.softwareheritage.org/wp-content/uploads/2021/03/msr-2020-challenge.pdf},

doi = {10.1145/3379597.3387510},

year  = {2020},

date = {2020-05-01},

booktitle = {MSR 2020: The 17th International Conference on Mining Software Repositories},

pages = {1-5},

publisher = {IEEE},

abstract = {Software Heritage is the largest existing public archive of software source code and accompanying development history. It spans more than five billion unique source code files and one billion unique commits, coming from more than 80 million software projects. These software artifacts were retrieved from major collaborative development platforms (e.g., GitHub, GitLab) and package repositories (e.g., PyPI, Debian, NPM), and stored in a uniform representation linking together source code files, directories, commits, and full snapshots of version control systems (VCS) repositories as observed by Software Heritage during periodic crawls. This dataset is unique in terms of accessibility and scale, and allows to explore a number of research questions on the long tail of public software development, instead of solely focusing on "most starred" repositories as it often happens.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{msr-2020-forks,

title = {Forking Without Clicking: on How to Identify Software Repository Forks},

author = {Antoine Pietri and Guillaume Rousseau and Stefano Zacchiroli},

url = {https://arxiv.org/abs/2011.07821 

https://www.softwareheritage.org/wp-content/uploads/2021/03/msr-2020-forks.pdf},

doi = {10.1145/3379597.3387450},

year  = {2020},

date = {2020-05-01},

booktitle = {MSR 2020: The 17th International Conference on Mining Software Repositories},

pages = {277-287},

publisher = {IEEE},

abstract = {The notion of software "fork" has been shifting over time from the (negative) phenomenon of community disagreements that result in the creation of separate development lines and ultimately software products, to the (positive) practice of using distributed version control system (VCS) repositories to collaboratively improve a single product without stepping on each others toes. In both cases the VCS repositories participating in a fork share parts of a common development history. Studies of software forks generally rely on hosting platform metadata, such as GitHub, as the source of truth for what constitutes a fork. These “forge forks” however can only identify as forks repositories that have been created on the platform, e.g., by clicking a "fork" button on the platform user interface. The increased diversity in code hosting platforms (e.g., GitLab) and the habits of significant development communities (e.g., the Linux kernel, which is not primarily hosted on any single platform) call into question the reliability of trusting code hosting platforms to identify forks. Doing so might introduce selection and methodological biases in empirical studies. In this article we explore various definitions of "software forks", trying to capture forking workflows that exist in the real world. We quantify the differences in how many repositories would be identified as forks on GitHub according to the various definitions, confirming that a significant number could be overlooked by only considering forge forks. We study the structure and size of fork networks, observing how they are affected by the proposed definitions and discuss the potential impact on empirical research.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{msr-2020-topology,

title = {Determining the Intrinsic Structure of Public Software Development History},

author = {Antoine Pietri and Guillaume Rousseau and Stefano Zacchiroli},

url = {https://arxiv.org/abs/2011.07914 

https://www.softwareheritage.org/wp-content/uploads/2021/03/msr-2020-topology.pdf},

doi = {10.1145/3379597.3387506},

year  = {2020},

date = {2020-05-01},

booktitle = {MSR 2020: The 17th International Conference on Mining Software Repositories},

pages = {602-605},

publisher = {IEEE},

abstract = {Background: Collaborative software development has produced a wealth of version control system (VCS) data that can now be analyzed in full. Little is known about the intrinsic structure of the entire corpus of publicly available VCS as an interconnected graph. Understanding its structure is needed to determine the best approach to analyze it in full and to avoid methodological pitfalls when doing so. Objective: We intend to determine the most salient network topology properties of public software development history as captured by VCS. We will explore: degree distributions, determining whether they are scale-free or not; distribution of connect component sizes; distribution of shortest path lengths. Method: We will use Software Heritage---which is the largest corpus of public VCS data---compress it using webgraph compression techniques, and analyze it in-memory using classic graph algorithms. Analyses will be performed both on the full graph and on relevant subgraphs. Limitations: The study is exploratory in nature; as such no hypotheses on the findings is stated at this time. Chosen graph algorithms are expected to scale to the corpus size, but it will need to be confirmed experimentally. External validity will depend on how representative Software Heritage is of the software commons.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{saner-2020-swh-graph,

title = {Ultra-Large-Scale Repository Analysis via Graph Compression},

author = {Paolo Boldi and Antoine Pietri and Sebastiano Vigna and Stefano Zacchiroli},

url = {https://www.softwareheritage.org/wp-content/uploads/2020/02/saner-2020-swh-graph.pdf 

https://upsilon.cc/~zack/research/publications/saner-2020-swh-graph.pdf},

doi = {10.1109/SANER48275.2020.9054827},

year  = {2020},

date = {2020-02-21},

booktitle = {SANER 2020: The 27th IEEE International Conference on Software Analysis, Evolution and Reengineering},

pages = {184-194},

publisher = {IEEE},

abstract = {We consider the problem of mining the development history—as captured by modern version control systems—of ultra-large-scale software archives (e.g., tens of millions software repositories corresponding). We show that graph compression techniques can be applied to the problem, dramatically reducing the hardware resources needed to mine similarly-sized corpus. As a concrete use case we compress the full Software Heritage archive, consisting of 5 billion unique source code files and 1 billion unique commits, harvested from more than 80 million software projects—encompassing a full mirror of GitHub. The resulting compressed graph fits in less than 100 GB of RAM, corresponding to a hardware cost of less than 300 U.S. dollars. We show that the compressed in-memory representation of the full corpus can be accessed with excellent performances, with edge lookup times close to memory random access. As a sample exploitation experiment we show that the compressed graph can be used to conduct clone detection at this scale, benefiting from main memory access speed.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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://www.softwareheritage.org/wp-content/uploads/2020/01/msr-2019-swh.pdf 

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://www.softwareheritage.org/wp-content/uploads/2020/01/benevol-2018-swh.pdf 

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}

}

@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://www.softwareheritage.org/wp-content/uploads/2020/01/ipres-2018-swh.pdf 

https://hal.archives-ouvertes.fr/hal-01865790},

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}

}

@inproceedings{dicosmo:hal-01590958,

title = {Software Heritage: Why and How to Preserve Software Source Code},

author = {Roberto Di Cosmo and Stefano Zacchiroli},

url = {https://www.softwareheritage.org/wp-content/uploads/2020/01/ipres-2017-swh.pdf 

https://hal.archives-ouvertes.fr/hal-01590958},

year  = {2017},

date = {2017-09-25},

booktitle = {iPRES 2017: 14th International Conference on Digital Preservation},

address = {Kyoto, Japan},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}