@article{corrado_digital_2022,
	title = {Digital {Preservation} {Is} {Not} {Just} a {Technology} {Problem}},
	volume = {39},
	issn = {0731-7131, 1555-3337},
	url = {https://www.tandfonline.com/doi/full/10.1080/07317131.2022.2045432},
	doi = {10.1080/07317131.2022.2045432},
	language = {en},
	number = {2},
	urldate = {2023-05-03},
	journal = {Technical Services Quarterly},
	author = {Corrado, Edward M.},
	month = apr,
	year = {2022},
	pages = {143--151},
}

@article{nirenberg_dostoevsky_2022,
	title = {Dostoevsky and the {Word} “{Jew}”: {A} {Quantitative} {Analysis} of {F}.{M}. {Dostoevsky}’s {Greatest} {Novels}},
	volume = {72},
	issn = {0024-2667, 1865-8423},
	shorttitle = {Dostoevsky and the {Word} “{Jew}”},
	url = {https://www.degruyter.com/document/doi/10.1515/libri-2021-0011/html},
	doi = {10.1515/libri-2021-0011},
	abstract = {Abstract
            The relationship of F.M Dostoevsky with Jews attracted the attention of numerous scholars throughout the years, many of whom attempted to grapple with the views of the great writer and their origin. In this article we will attempt to show this relationship by analyzing six of Dostoevsky’s greatest novels, written through the entirety of his career. We are analyzing these novels using Distant Reading in conjunction with Close Reading, tools that are commonly used in the field of digital humanities, which enabled us to show visually the extent of F.M. Dostoevsky’s engagement with this topic. The study poses two research questions: 1. To what extent did the writer use the more denigrating term “Zhid”? 2. Can we see a correlation between the writer’s portrayal of Jews with the definition of Anti-Semitism as it was known during his era? The obtained results show that there is clearly a correlation between the definition of anti-Semitism as it was understood at the time of Dostoevsky and the “Jew” as depicted in his novels, as the financial motif is paramount in the depiction of Jews as this is the central topic in 49\% of the negative sentences in which the word “Jew” appears, with 59\% of these sentences classified as stereotypes. The negative financial stereotype constitutes 32\% of the entire corpus. In addition, we found the term “Zhid” is commonly used by the writer, a variation of which constitutes 75\% of the total terms used to depict Jews.},
	language = {en},
	number = {1},
	urldate = {2023-05-03},
	journal = {Libri},
	author = {Nirenberg, Yigal and Prebor, Gila},
	month = mar,
	year = {2022},
	pages = {83--96},
}

Abstract The relationship of F.M Dostoevsky with Jews attracted the attention of numerous scholars throughout the years, many of whom attempted to grapple with the views of the great writer and their origin. In this article we will attempt to show this relationship by analyzing six of Dostoevsky’s greatest novels, written through the entirety of his career. We are analyzing these novels using Distant Reading in conjunction with Close Reading, tools that are commonly used in the field of digital humanities, which enabled us to show visually the extent of F.M. Dostoevsky’s engagement with this topic. The study poses two research questions: 1. To what extent did the writer use the more denigrating term “Zhid”? 2. Can we see a correlation between the writer’s portrayal of Jews with the definition of Anti-Semitism as it was known during his era? The obtained results show that there is clearly a correlation between the definition of anti-Semitism as it was understood at the time of Dostoevsky and the “Jew” as depicted in his novels, as the financial motif is paramount in the depiction of Jews as this is the central topic in 49% of the negative sentences in which the word “Jew” appears, with 59% of these sentences classified as stereotypes. The negative financial stereotype constitutes 32% of the entire corpus. In addition, we found the term “Zhid” is commonly used by the writer, a variation of which constitutes 75% of the total terms used to depict Jews.

@article{adams_online_2021,
	title = {Online tools for digital humanities},
	volume = {17},
	issn = {1522-8959, 1522-9114},
	url = {https://www.tandfonline.com/doi/full/10.1080/15228959.2021.1938789},
	doi = {10.1080/15228959.2021.1938789},
	language = {en},
	number = {3},
	urldate = {2023-05-18},
	journal = {Public Services Quarterly},
	author = {Adams, Annis Lee},
	month = jul,
	year = {2021},
	pages = {177--182},
}

@article{jaaskelainen_citizen_2021,
	title = {Citizen {Archive}: {My} {Precious} {Information}},
	volume = {26},
	issn = {1361-4576, 1740-7869},
	shorttitle = {Citizen {Archive}},
	url = {https://www.tandfonline.com/doi/full/10.1080/13614576.2018.1537800},
	doi = {10.1080/13614576.2018.1537800},
	language = {en},
	number = {1-2},
	urldate = {2023-05-18},
	journal = {New Review of Information Networking},
	author = {Jääskeläinen, Anssi and Uosukainen, Liisa},
	month = jul,
	year = {2021},
	pages = {1--11},
}

@article{narlock_digital_2021,
	title = {Digital preservation services at digital scholarship centers},
	volume = {47},
	issn = {00991333},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0099133321000252},
	doi = {10.1016/j.acalib.2021.102334},
	language = {en},
	number = {3},
	urldate = {2023-05-17},
	journal = {The Journal of Academic Librarianship},
	author = {Narlock, Mikala and Johnson, Daniel and Vecchio, Julie},
	month = may,
	year = {2021},
	pages = {102334},
}

@article{rakityanskaya_video_2021,
	title = {Video {Appeals} to the {President} of {Russia}: {Creating} a {Born}-{Digital} {Primary} {Source} {Collection}},
	volume = {22},
	issn = {1522-8886, 1522-9041},
	shorttitle = {Video {Appeals} to the {President} of {Russia}},
	url = {https://www.tandfonline.com/doi/full/10.1080/15228886.2021.2018250},
	doi = {10.1080/15228886.2021.2018250},
	language = {en},
	number = {3-4},
	urldate = {2023-05-06},
	journal = {Slavic \& East European Information Resources},
	author = {Rakityanskaya, Anna},
	month = oct,
	year = {2021},
	pages = {344--355},
}

@inproceedings{kalcso_born_2021,
	title = {Born digital workflow tervezése a {Petőfi} {Irodalmi} {Múzeum} {Digitális} {Bölcsészeti} {Központjában}},
	isbn = {978-615-01-2956-3},
	url = {http://ocs.mtak.hu/index.php/nws/2021/paper/view/78},
	doi = {10.31915/NWS.2021.20},
	abstract = {The Petőfi Literary Museum’s Digital Humanities Centre, established last year, is in the process of creating a digital humanities platform, dHUpla. One of its sub-areas is the planning of the management of born digital materials. The development of a procedure for born digital materials is an urgent need: in addition to the existing collection items in the PIM, it is expected that in the future more and more content of this kind will be created, which will need to be managed professionally. The presentation will describe the research work carried out and the details of the workflow that is being outlined. It will present the workflow developed on the basis of the OAIS model, which covers the process from ingestion of such material to making it searchable and publishable. It covers not only the more manageable text file formats of born digital content, but also the more difficult tasks of emails or social media sites, and how to professionally extract and archive data from external media.},
	urldate = {2022-06-16},
	booktitle = {Online térben az online térért : {Networkshop} 30: országos online konferencia. 2021. április 6-9. {Eötvös} {Loránd} {Tudományegyetem}},
	publisher = {HUNGARNET Egyesület},
	author = {Kalcsó, Gyula},
	year = {2021},
	pages = {195--203},
}

The Petőfi Literary Museum’s Digital Humanities Centre, established last year, is in the process of creating a digital humanities platform, dHUpla. One of its sub-areas is the planning of the management of born digital materials. The development of a procedure for born digital materials is an urgent need: in addition to the existing collection items in the PIM, it is expected that in the future more and more content of this kind will be created, which will need to be managed professionally. The presentation will describe the research work carried out and the details of the workflow that is being outlined. It will present the workflow developed on the basis of the OAIS model, which covers the process from ingestion of such material to making it searchable and publishable. It covers not only the more manageable text file formats of born digital content, but also the more difficult tasks of emails or social media sites, and how to professionally extract and archive data from external media.

@book{szatucsek_az_2021,
	address = {Budapest},
	title = {Az elektronikus iratok kezelése},
	url = {https://kti.uni-nke.hu/document/vtkk-uni-nke-hu/Az%20elektronikus%20iratok%20kezel%C3%A9se.pdf},
	publisher = {Nemzeti Közszolgálati Egyetem Közigazgatási Továbbképzési Intézet},
	author = {Szatucsek, Zoltán},
	year = {2021},
}

@article{lee_deduplicating_2021,
	title = {Deduplicating {Training} {Data} {Makes} {Language} {Models} {Better}},
	copyright = {arXiv.org perpetual, non-exclusive license},
	url = {https://arxiv.org/abs/2107.06499},
	doi = {10.48550/ARXIV.2107.06499},
	abstract = {We find that existing language modeling datasets contain many near-duplicate examples and long repetitive substrings. As a result, over 1\% of the unprompted output of language models trained on these datasets is copied verbatim from the training data. We develop two tools that allow us to deduplicate training datasets -- for example removing from C4 a single 61 word English sentence that is repeated over 60,000 times. Deduplication allows us to train models that emit memorized text ten times less frequently and require fewer train steps to achieve the same or better accuracy. We can also reduce train-test overlap, which affects over 4\% of the validation set of standard datasets, thus allowing for more accurate evaluation. We release code for reproducing our work and performing dataset deduplication at https://github.com/google-research/deduplicate-text-datasets.},
	urldate = {2022-06-07},
	author = {Lee, Katherine and Ippolito, Daphne and Nystrom, Andrew and Zhang, Chiyuan and Eck, Douglas and Callison-Burch, Chris and Carlini, Nicholas},
	year = {2021},
	note = {Publisher: arXiv
Version Number: 2},
	keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, Machine Learning (cs.LG)},
}

We find that existing language modeling datasets contain many near-duplicate examples and long repetitive substrings. As a result, over 1% of the unprompted output of language models trained on these datasets is copied verbatim from the training data. We develop two tools that allow us to deduplicate training datasets – for example removing from C4 a single 61 word English sentence that is repeated over 60,000 times. Deduplication allows us to train models that emit memorized text ten times less frequently and require fewer train steps to achieve the same or better accuracy. We can also reduce train-test overlap, which affects over 4% of the validation set of standard datasets, thus allowing for more accurate evaluation. We release code for reproducing our work and performing dataset deduplication at https://github.com/google-research/deduplicate-text-datasets.

@article{erickson_plain_2021,
	title = {Plain {Text} \& {Character} {Encoding}: {A} {Primer} for {Data} {Curators}},
	volume = {10},
	issn = {21613974},
	shorttitle = {Plain {Text} \& {Character} {Encoding}},
	url = {https://escholarship.umassmed.edu/jeslib/vol10/iss3/12/},
	doi = {10.7191/jeslib.2021.1211},
	abstract = {Plain text data consists of a sequence of encoded characters or “code points” from a given standard such as the Unicode Standard. Some of the most common file formats for digital data used in eScience (CSV, XML, and JSON, for example) are built atop plain text standards. Plain text representations of digital data are often preferred because plain text formats are relatively stable, and they facilitate reuse and interoperability. Despite its ubiquity, plain text is not as plain as it may seem. The set of standards used in modern text encoding (principally, the Unicode Character Set and the related encoding format, UTF-8) have complex architectures when compared to historical standards like ASCII. Further, while the Unicode standard has gained in prominence, text encoding problems are not uncommon in research data curation. This primer provides conceptual foundations for modern text encoding and guidance for common curation and preservation actions related to textual data.},
	number = {3},
	urldate = {2022-05-05},
	journal = {Journal of eScience Librarianship},
	author = {Erickson, Seth},
	month = aug,
	year = {2021},
	pages = {1211},
}

Plain text data consists of a sequence of encoded characters or “code points” from a given standard such as the Unicode Standard. Some of the most common file formats for digital data used in eScience (CSV, XML, and JSON, for example) are built atop plain text standards. Plain text representations of digital data are often preferred because plain text formats are relatively stable, and they facilitate reuse and interoperability. Despite its ubiquity, plain text is not as plain as it may seem. The set of standards used in modern text encoding (principally, the Unicode Character Set and the related encoding format, UTF-8) have complex architectures when compared to historical standards like ASCII. Further, while the Unicode standard has gained in prominence, text encoding problems are not uncommon in research data curation. This primer provides conceptual foundations for modern text encoding and guidance for common curation and preservation actions related to textual data.

@article{vlassenroot_web-archiving_2021,
	title = {Web-archiving and social media: an exploratory analysis: {Call} for papers digital humanities and web archives – {A} special issue of international journal of digital humanities},
	volume = {2},
	issn = {2524-7832, 2524-7840},
	shorttitle = {Web-archiving and social media},
	url = {https://link.springer.com/10.1007/s42803-021-00036-1},
	doi = {10.1007/s42803-021-00036-1},
	language = {en},
	number = {1-3},
	urldate = {2022-02-07},
	journal = {International Journal of Digital Humanities},
	author = {Vlassenroot, Eveline and Chambers, Sally and Lieber, Sven and Michel, Alejandra and Geeraert, Friedel and Pranger, Jessica and Birkholz, Julie and Mechant, Peter},
	month = nov,
	year = {2021},
	pages = {107--128},
}

@techreport{noauthor_born_2021,
	title = {Born digital archive cataloguing and description},
	url = {https://www.dpconline.org/docs/technology-watch-reports/2468-born-digital-archive-cataloguing-and-description/file},
	urldate = {2021-09-23},
	institution = {Digital Preservation Coalition},
	month = may,
	year = {2021},
	doi = {10.7207/twgn21-05},
}

@article{velte_scalable_2020,
	title = {Scalable {Born} {Digital} {Ingest} {Workflows} for {Limited} {Resources}: {A} {Case} {Study} for {First} {Steps} in {Digital} {Preservation}},
	volume = {49},
	issn = {2195-2965, 2195-2957},
	shorttitle = {Scalable {Born} {Digital} {Ingest} {Workflows} for {Limited} {Resources}},
	url = {https://www.degruyter.com/document/doi/10.1515/pdtc-2020-0004/html},
	doi = {10.1515/pdtc-2020-0004},
	abstract = {Abstract
            This article seeks to provide an example of a scalable and achievable born digital ingest workflow for cultural heritage institutions of any size, including those with limited funding. Like many small archives, the University of Idaho (U of I) Library Special Collections and Archives (SPEC) has accepted born digital material when it arrives as part of analog collections for the last 20 years. However, the Library has faced numerous challenges similar to those of other small institutions when developing workflows for born digital preservation and ingest. These include lack of funding, systems, and policies. Despite a growing number of resources that support digital preservation work, among current best practices it is difficult to find scalable workflows for institutions with limited staff and funds. By implementing accessible open-source software and prioritizing preservation tasks, U of I Library has developed a low-cost way to implement systems for digital preservation with responsibilities that can be spread out among librarians and archivists with varying technical expertise.},
	language = {en},
	number = {1},
	urldate = {2024-07-08},
	journal = {Preservation, Digital Technology \& Culture},
	author = {Velte, Ashlyn and Wikle, Olivia M.},
	month = apr,
	year = {2020},
	pages = {2--13},
}

Abstract This article seeks to provide an example of a scalable and achievable born digital ingest workflow for cultural heritage institutions of any size, including those with limited funding. Like many small archives, the University of Idaho (U of I) Library Special Collections and Archives (SPEC) has accepted born digital material when it arrives as part of analog collections for the last 20 years. However, the Library has faced numerous challenges similar to those of other small institutions when developing workflows for born digital preservation and ingest. These include lack of funding, systems, and policies. Despite a growing number of resources that support digital preservation work, among current best practices it is difficult to find scalable workflows for institutions with limited staff and funds. By implementing accessible open-source software and prioritizing preservation tasks, U of I Library has developed a low-cost way to implement systems for digital preservation with responsibilities that can be spread out among librarians and archivists with varying technical expertise.

@inproceedings{dimitrov_tweetscov19_2020,
	title = {{TweetsCOV19} -- {A} {Knowledge} {Base} of {Semantically} {Annotated} {Tweets} about the {COVID}-19 {Pandemic}},
	url = {http://arxiv.org/abs/2006.14492},
	doi = {10.1145/3340531.3412765},
	abstract = {Publicly available social media archives facilitate research in the social sciences and provide corpora for training and testing a wide range of machine learning and natural language processing methods. With respect to the recent outbreak of the Coronavirus disease 2019 (COVID-19), online discourse on Twitter reflects public opinion and perception related to the pandemic itself as well as mitigating measures and their societal impact. Understanding such discourse, its evolution, and interdependencies with real-world events or (mis)information can foster valuable insights. On the other hand, such corpora are crucial facilitators for computational methods addressing tasks such as sentiment analysis, event detection, or entity recognition. However, obtaining, archiving, and semantically annotating large amounts of tweets is costly. In this paper, we describe TweetsCOV19, a publicly available knowledge base of currently more than 8 million tweets, spanning October 2019 - April 2020. Metadata about the tweets as well as extracted entities, hashtags, user mentions, sentiments, and URLs are exposed using established RDF/S vocabularies, providing an unprecedented knowledge base for a range of knowledge discovery tasks. Next to a description of the dataset and its extraction and annotation process, we present an initial analysis and use cases of the corpus.},
	urldate = {2024-03-04},
	booktitle = {Proceedings of the 29th {ACM} {International} {Conference} on {Information} \& {Knowledge} {Management}},
	author = {Dimitrov, Dimitar and Baran, Erdal and Fafalios, Pavlos and Yu, Ran and Zhu, Xiaofei and Zloch, Matthäus and Dietze, Stefan},
	month = oct,
	year = {2020},
	note = {arXiv:2006.14492 [cs]},
	keywords = {Computer Science - Information Retrieval, Computer Science - Social and Information Networks},
	pages = {2991--2998},
}

Publicly available social media archives facilitate research in the social sciences and provide corpora for training and testing a wide range of machine learning and natural language processing methods. With respect to the recent outbreak of the Coronavirus disease 2019 (COVID-19), online discourse on Twitter reflects public opinion and perception related to the pandemic itself as well as mitigating measures and their societal impact. Understanding such discourse, its evolution, and interdependencies with real-world events or (mis)information can foster valuable insights. On the other hand, such corpora are crucial facilitators for computational methods addressing tasks such as sentiment analysis, event detection, or entity recognition. However, obtaining, archiving, and semantically annotating large amounts of tweets is costly. In this paper, we describe TweetsCOV19, a publicly available knowledge base of currently more than 8 million tweets, spanning October 2019 - April 2020. Metadata about the tweets as well as extracted entities, hashtags, user mentions, sentiments, and URLs are exposed using established RDF/S vocabularies, providing an unprecedented knowledge base for a range of knowledge discovery tasks. Next to a description of the dataset and its extraction and annotation process, we present an initial analysis and use cases of the corpus.

@inproceedings{gyawali_deduplication_2020,
	address = {Marseille, France},
	title = {Deduplication of {Scholarly} {Documents} using {Locality} {Sensitive} {Hashing} and {Word} {Embeddings}},
	isbn = {979-10-95546-34-4},
	url = {https://aclanthology.org/2020.lrec-1.113},
	abstract = {Deduplication is the task of identifying near and exact duplicate data items in a collection. In this paper, we present a novel method for deduplication of scholarly documents. We develop a hybrid model which uses structural similarity (locality sensitive hashing) and meaning representation (word embeddings) of document texts to determine (near) duplicates. Our collection constitutes a subset of multidisciplinary scholarly documents aggregated from research repositories. We identify several issues causing data inaccuracies in such collections and motivate the need for deduplication. In lack of existing dataset suitable for study of deduplication of scholarly documents, we create a ground truth dataset of \$100K\$ scholarly documents and conduct a series of experiments to empirically establish optimal values for the parameters of our deduplication method. Experimental evaluation shows that our method achieves a macro F1-score of 0.90. We productionise our method as a publicly accessible web API service serving deduplication of scholarly documents in real time.},
	language = {English},
	booktitle = {Proceedings of the 12th {Language} {Resources} and {Evaluation} {Conference}},
	publisher = {European Language Resources Association},
	author = {Gyawali, Bikash and Anastasiou, Lucas and Knoth, Petr},
	year = {2020},
	pages = {901--910},
}

Deduplication is the task of identifying near and exact duplicate data items in a collection. In this paper, we present a novel method for deduplication of scholarly documents. We develop a hybrid model which uses structural similarity (locality sensitive hashing) and meaning representation (word embeddings) of document texts to determine (near) duplicates. Our collection constitutes a subset of multidisciplinary scholarly documents aggregated from research repositories. We identify several issues causing data inaccuracies in such collections and motivate the need for deduplication. In lack of existing dataset suitable for study of deduplication of scholarly documents, we create a ground truth dataset of $100K$ scholarly documents and conduct a series of experiments to empirically establish optimal values for the parameters of our deduplication method. Experimental evaluation shows that our method achieves a macro F1-score of 0.90. We productionise our method as a publicly accessible web API service serving deduplication of scholarly documents in real time.

@inproceedings{k_g_open_2020,
	title = {Open {Source} {Software} for {Digital} {Archiving}: {A} {Comparative} {Study} on {RODA} and {Archivematica}},
	author = {K G, Sudhier and Abhijith, B},
	year = {2020},
}

@inproceedings{ge_text_2019,
	address = {Zhuhai, China},
	title = {Text {Deduplication} with {Minimum} {Loss} {Ratio}},
	isbn = {978-1-4503-6600-7},
	url = {http://dl.acm.org/citation.cfm?doid=3318299.3318369},
	doi = {10.1145/3318299.3318369},
	language = {en},
	urldate = {2022-06-07},
	booktitle = {Proceedings of the 2019 11th {International} {Conference} on {Machine} {Learning} and {Computing}  - {ICMLC} '19},
	publisher = {ACM Press},
	author = {Ge, Youming and Wu, Jiefeng and Dai, Genan and Liu, Yubao},
	year = {2019},
	pages = {310--316},
}

@book{banki_feher_2019,
	title = {Fehér könyv. {Módszertani} útmutató a közgyűjteményi kulturális örökség digitalizálásához és közzétételéhez},
	url = {https://ommik.hu/media/attachments/2019/12/09/fehr_knyv.pdf},
	publisher = {Emberi Erőforrások Minisztériuma},
	editor = {Bánki, Zsolt and Kómár, Éva},
	year = {2019},
}

@article{jaillant_after_2019,
	title = {After the digital revolution: working with emails and born-digital records in literary and publishers’ archives},
	volume = {47},
	issn = {0157-6895, 2164-6058},
	shorttitle = {After the digital revolution},
	url = {https://www.tandfonline.com/doi/full/10.1080/01576895.2019.1640555},
	doi = {10.1080/01576895.2019.1640555},
	language = {en},
	number = {3},
	urldate = {2021-01-29},
	journal = {Archives and Manuscripts},
	author = {Jaillant, Lise},
	month = sep,
	year = {2019},
	pages = {285--304},
}

@book{myntii_digital_2019,
	address = {Chicago},
	series = {An {ALCTS} monograph},
	title = {Digital preservation in libraries: preparing for a sustainable future},
	isbn = {978-0-8389-1713-8 978-0-8389-1745-9 978-0-8389-1744-2 978-0-8389-1746-6},
	shorttitle = {Digital preservation in libraries},
	language = {eng},
	publisher = {ALA Editions},
	editor = {Myntii, Jeremy and Zoom, Jessalyn and American Library Association and Association for Library Collections \& Technical Services},
	year = {2019},
	note = {OCLC: 1043858531},
}

@book{jin_designing_2018,
	title = {Designing {Web} {APIs}: {Building} {APIs} {That} {Developers} {Love}},
	isbn = {978-1-4920-2687-7},
	url = {https://books.google.hu/books?id=Dg1rDwAAQBAJ},
	publisher = {O'Reilly Media},
	author = {Jin, B. and Sahni, S. and Shevat, A.},
	year = {2018},
}

@article{fondren_archiving_2018,
	title = {Archiving and {Preserving} {Social} {Media} at the {Library} of {Congress}: {Institutional} and {Cultural} {Challenges} to {Build} a {Twitter} {Archive}},
	volume = {47},
	issn = {2195-2965, 2195-2957},
	shorttitle = {Archiving and {Preserving} {Social} {Media} at the {Library} of {Congress}},
	url = {https://www.degruyter.com/document/doi/10.1515/pdtc-2018-0011/html},
	doi = {10.1515/pdtc-2018-0011},
	abstract = {Abstract
            Institutional archiving of media is neither new nor strange. The United States Library of Congress has been preserving printed materials, newspapers, photographs, film, and even websites for decades—if not centuries. After seven years, in later 2017, the initiative to build a Twitter Archive came to a halt. Through a textual analysis of policy papers, preservation theories and press releases, this study illustrates the social, cultural, and symbolic challenges of institutional archiving of digital media.},
	number = {2},
	urldate = {2023-11-06},
	journal = {Preservation, Digital Technology \& Culture},
	author = {Fondren, Elisabeth and Menard McCune, Meghan},
	month = jul,
	year = {2018},
	pages = {33--44},
}

Abstract Institutional archiving of media is neither new nor strange. The United States Library of Congress has been preserving printed materials, newspapers, photographs, film, and even websites for decades—if not centuries. After seven years, in later 2017, the initiative to build a Twitter Archive came to a halt. Through a textual analysis of policy papers, preservation theories and press releases, this study illustrates the social, cultural, and symbolic challenges of institutional archiving of digital media.

@book{andrew_w_mellon_foundation_future_2018,
	address = {Washington, DC},
	series = {{CLIR} publication},
	title = {The future of email archives: a report from the {Task} {Force} on {Technical} {Approaches} for {Email} {Archives}, {August} 2018},
	isbn = {978-1-932326-59-8},
	shorttitle = {The future of email archives},
	url = {https://clir.wordpress.clir.org/wp-content/uploads/sites/6/2018/08/CLIR-pub175.pdf},
	number = {no. 175},
	publisher = {Council on Library and Information Resources},
	editor = {{Andrew W. Mellon Foundation} and {Digital Preservation Coalition}},
	year = {2018},
	note = {OCLC: on1049574908},
	keywords = {Digital preservation, Electronic mail messages, Electronic records},
}

@techreport{langley_cambridge_2018,
	title = {Cambridge {University} {Libraries} {Digital} {Preservation} {Policy}},
	copyright = {Attribution-NonCommercial 4.0 International, Attribution-NonCommercial 4.0 International, Attribution-NonCommercial 4.0 International, Creative Commons Attribution Non Commercial 4.0 International, Creative Commons Attribution Non Commercial 4.0 International, Creative Commons Attribution Non Commercial 4.0 International},
	url = {https://www.repository.cam.ac.uk/handle/1810/285707},
	abstract = {The Digital Preservation Policy (the Policy) sets out the duties and responsibilities for Cambridge University Libraries’ (CUL) stewardship of digital content. This Policy applies to the main University Library as well as affiliate and dependent libraries. The Policy provides the overarching framework for supporting the management of digital content (encompassing born-digital and digitised content).},
	urldate = {2020-08-03},
	institution = {Apollo - University of Cambridge Repository},
	author = {Langley, Somaya},
	collaborator = {Apollo-University Of Cambridge Repository and Apollo-University Of Cambridge Repository},
	month = nov,
	year = {2018},
	doi = {10.17863/CAM.32927},
	keywords = {Cambridge University Libraries, Cambridge University Library, DPOC, Digital Preservation Policy, Digital Preservation at Oxford and Cambridge, digital preservation, policy},
}

The Digital Preservation Policy (the Policy) sets out the duties and responsibilities for Cambridge University Libraries’ (CUL) stewardship of digital content. This Policy applies to the main University Library as well as affiliate and dependent libraries. The Policy provides the overarching framework for supporting the management of digital content (encompassing born-digital and digitised content).

@misc{fairsharing_team_fairsharing_2018,
	title = {{FAIRsharing} record for: {NISO} {Metadata} for {Images} in {XML} {Schema}},
	shorttitle = {{FAIRsharing} record for},
	url = {https://fairsharing.org/FAIRsharing.riJmuf},
	doi = {10.25504/FAIRSHARING.RIJMUF},
	abstract = {This FAIRsharing record describes: The XML-based schema for encoding the NISO Data Dictionary - Technical Metadata for Digital Still Images (ANSI/NISO Z39.87-2006).},
	urldate = {2021-09-22},
	publisher = {FAIRsharing},
	author = {FAIRsharing Team},
	year = {2018},
	keywords = {Computer Science, Data sharing, Data storage, General purpose, Image, Metadata standardization},
}

This FAIRsharing record describes: The XML-based schema for encoding the NISO Data Dictionary - Technical Metadata for Digital Still Images (ANSI/NISO Z39.87-2006).

@book{kunze_bagit_2018,
	series = {Request for {Comments}},
	title = {The {BagIt} {File} {Packaging} {Format} ({V1}.0)},
	url = {https://rfc-editor.org/rfc/rfc8493.txt},
	abstract = {This document describes BagIt, a set of hierarchical file layout conventions for storage and transfer of arbitrary digital content. A "bag" has just enough structure to enclose descriptive metadata "tags" and a file "payload" but does not require knowledge of the payload's internal semantics. This BagIt format is suitable for reliable storage and transfer.},
	number = {8493},
	publisher = {RFC Editor},
	author = {Kunze, John A. and Littman, Justin and Madden, Liz and Scancella, John and Adams, Chris},
	year = {2018},
	doi = {10.17487/RFC8493},
	note = {Published: RFC 8493},
}

This document describes BagIt, a set of hierarchical file layout conventions for storage and transfer of arbitrary digital content. A "bag" has just enough structure to enclose descriptive metadata "tags" and a file "payload" but does not require knowledge of the payload's internal semantics. This BagIt format is suitable for reliable storage and transfer.

@incollection{langley_digital_2018,
	title = {Digital {Preservation} {Should} {Be} {More} {Holistic}: {A} {Digital} {Stewardship} {Approach}},
	shorttitle = {Digital {Preservation} {Should} {Be} {More} {Holistic}},
	url = {https://www.repository.cam.ac.uk/handle/1810/287006},
	abstract = {A considerable amount of creative, cultural, and research output is expressed in digital form. It is imperative that the memory sector rapidly improve its capability and capacity for handling digital content in all forms, including complex data. It took gallery, library, archive, and museum (GLAM) sector institutions somewhere between decades and centuries to implement systems for managing physical collections. Those who work with digital content are acutely aware that the same time frames are not afforded when it comes to saving our digital cultural heritage. The “fragility” of content produced from computing environments — thanks to the rapid churn of technological innovation and obsolescence — means that even acquiring, preserving, and providing sustained access to a seemingly “simple” stand-alone file can take considerable effort. The interdependencies and limitations of the computing platforms, software, hardware, and other peripherals (whether mass-manufactured or custom-developed) bring a level of complexity that is typically not experienced with physical collections.},
	urldate = {2021-06-15},
	publisher = {Apollo - University of Cambridge Repository},
	author = {Langley, Somaya},
	collaborator = {Apollo-University Of Cambridge Repository and Apollo-University Of Cambridge Repository and Myntti, J and Zoom, J},
	month = dec,
	year = {2018},
	doi = {10.17863/CAM.34317},
	keywords = {Digital Stewardship End-to-End Workflow Model, Digital Streams Matrix, born-digital, digital content, digital curation, digital preservation, digital stewardship, digital workflows},
}

A considerable amount of creative, cultural, and research output is expressed in digital form. It is imperative that the memory sector rapidly improve its capability and capacity for handling digital content in all forms, including complex data. It took gallery, library, archive, and museum (GLAM) sector institutions somewhere between decades and centuries to implement systems for managing physical collections. Those who work with digital content are acutely aware that the same time frames are not afforded when it comes to saving our digital cultural heritage. The “fragility” of content produced from computing environments — thanks to the rapid churn of technological innovation and obsolescence — means that even acquiring, preserving, and providing sustained access to a seemingly “simple” stand-alone file can take considerable effort. The interdependencies and limitations of the computing platforms, software, hardware, and other peripherals (whether mass-manufactured or custom-developed) bring a level of complexity that is typically not experienced with physical collections.

@inproceedings{hutchinson_protecting_2018,
	title = {Protecting {Privacy} in the {Archives}: {Supervised} {Machine} {Learning} and {Born}-{Digital} {Records}},
	doi = {10.1109/BigData.2018.8621929},
	booktitle = {2018 {IEEE} {International} {Conference} on {Big} {Data} ({Big} {Data})},
	author = {Hutchinson, Tim},
	year = {2018},
	pages = {2696--2701},
}

@article{muhanna_what_2018,
	title = {What {Does} “{Born} {Digital}” {Mean}?},
	volume = {50},
	issn = {0020-7438, 1471-6380},
	url = {https://www.cambridge.org/core/product/identifier/S0020743817000976/type/journal_article},
	doi = {10.1017/S0020743817000976},
	abstract = {When asked for a definition of the digital humanities, I often fall back on a crisp formula. Digital humanists use computation to generate, organize, publish, or interpret humanistic data. This covers most of the bases, but it's also a bit abstract. “What sort of computation?” a colleague sometimes asks. “I use a computer at work; why aren't I a digital humanist?” To this, I agree; there isn't much daylight between digital and analogue scholarship. Less interesting than what separates the two domains is the question of what unites them. In my view, the most significant shared ingredient is technology.},
	language = {en},
	number = {1},
	urldate = {2020-09-10},
	journal = {International Journal of Middle East Studies},
	author = {Muhanna, Elias},
	month = feb,
	year = {2018},
	pages = {110--112},
}

When asked for a definition of the digital humanities, I often fall back on a crisp formula. Digital humanists use computation to generate, organize, publish, or interpret humanistic data. This covers most of the bases, but it's also a bit abstract. “What sort of computation?” a colleague sometimes asks. “I use a computer at work; why aren't I a digital humanist?” To this, I agree; there isn't much daylight between digital and analogue scholarship. Less interesting than what separates the two domains is the question of what unites them. In my view, the most significant shared ingredient is technology.

@book{group_uc_2018,
	title = {{UC} {Guidelines} for {Born}-{Digital} {Archival} {Description}},
	shorttitle = {uc-guidelines},
	url = {https://github.com/uc-borndigital-ckg/uc-guidelines},
	author = {Group, University of California Born-Digital Content Common Knowledge},
	year = {2018},
	keywords = {descriptive-standard, digital-archives, library-special-collections, metadata, university-of-california},
}

@article{dancs_hiteles_2017,
	title = {A hiteles digitális másolatról és a másolati példányok bibliográfiai kezeléséről – 2. rész: {Metaadatok}},
	volume = {26},
	number = {12},
	journal = {Könyv, Könyvtár, Könyvtáros},
	author = {Dancs, Szabolcs},
	year = {2017},
	pages = {7--14},
}

@article{dancs_hiteles_2017-1,
	title = {A hiteles digitális másolatról és a másolati példányok bibliográfiai kezeléséről – 1. rész: {Hitelesség} szabványos alapokon},
	volume = {26},
	number = {10},
	journal = {Könyv, Könyvtár, Könyvtáros},
	author = {Dancs, Szabolcs},
	year = {2017},
	pages = {7--15},
}

@article{rosa_open_2017,
	title = {Open {Source} {Software} for {Digital} {Preservation} {Repositories} : {A} {Survey}},
	volume = {8},
	issn = {09763252, 09762760},
	shorttitle = {Open {Source} {Software} for {Digital} {Preservation} {Repositories}},
	url = {http://aircconline.com/ijcses/V8N3/8317ijcses02.pdf},
	doi = {10.5121/ijcses.2017.8302},
	number = {3},
	urldate = {2021-05-12},
	journal = {International Journal of Computer Science \& Engineering Survey},
	author = {Rosa, Carlos André and Craveiro, Olga and Domingues, Patricio},
	month = jun,
	year = {2017},
	pages = {21--39},
}

@article{dancs_hosszu_2016,
	title = {A hosszú távú megőrzés szabványos útja(és a {Rosetta} rendszer példája)},
	volume = {63},
	number = {1},
	journal = {Tudományos és Műszaki Tájékoztatás},
	author = {Dancs, Szabolcs},
	year = {2016},
	pages = {27--37},
}

@book{elings_using_2016,
	title = {Using {NLP} to {Support} {Dynamic} {Arrangement}, {Description}, and {Discovery} of {Born} {Digital} {Collections}: {The} {ArchExtract} {Experiment}},
	url = {https://saaers.wordpress.com/2016/05/24/using-nlp-to-support-dynamic-arrangement-description-and-discovery-of-born-digital-collections-the-archextract-experiment/},
	abstract = {This post is the eighth in SAA'S ELECTRONIC RECORDS SECTION Spring 2016 series on processing digital materials.},
	author = {Elings, Mary W.},
	year = {2016},
	note = {Publication Title: BLOGGERS!
Type: THE BLOG OF SAA'S ELECTRONIC RECORDS SECTION},
}

This post is the eighth in SAA'S ELECTRONIC RECORDS SECTION Spring 2016 series on processing digital materials.

@book{davis_pathways_2016,
	title = {Pathways to {Automated} {Appraisal} for {Born}-{Digital} {Records}: {An} {SAA} 2016 {ERS} {Breakout} {Discussion} {Recap}},
	url = {https://saaers.wordpress.com/2016/10/21/pathways-to-automated-appraisal-for-born-digital-records-an-saa-2016-ers-breakout-discussion-recap/},
	abstract = {An SAA 2016 ERS Breakout Discussion Recap},
	author = {Davis, Lora},
	year = {2016},
	note = {Publication Title: BLOGGERS!
Type: THE BLOG OF SAA'S ELECTRONIC RECORDS SECTION},
}

An SAA 2016 ERS Breakout Discussion Recap

@book{olson_recent_2016,
	title = {Recent {Changes} in {How} {Stanford} {University} {Libraries} is {Documenting} {Born}-{Digital} {Processing}},
	url = {https://saaers.wordpress.com/2016/04/19/recent-changes-in-how-stanford-university-libraries-is-documenting-born-digital-processing/},
	abstract = {This post is the third in SAA'S ELECTRONIC RECORDS SECTION Spring 2016 series on processing digital materials.},
	author = {Olson, Michael G.},
	year = {2016},
	note = {Publication Title: BLOGGERS!
Type: THE BLOG OF SAA'S ELECTRONIC RECORDS SECTION},
}

This post is the third in SAA'S ELECTRONIC RECORDS SECTION Spring 2016 series on processing digital materials.

@book{white_politics_2016,
	title = {Politics, {Transparency}, and {Email}: {Lessons} {Learned} from {Trying} to {Preserve} the {Historical} {Record}},
	url = {https://saaers.wordpress.com/2016/06/21/politics-transparency-and-email-lessons-learned-from-trying-to-preserve-the-historical-record/},
	abstract = {This post is the ninth in SAA'S ELECTRONIC RECORDS SECTION Spring 2016 series on processing digital materials.},
	author = {White, Angela},
	year = {2016},
	note = {Publication Title: BLOGGERS!
Type: THE BLOG OF SAA'S ELECTRONIC RECORDS SECTION},
}

This post is the ninth in SAA'S ELECTRONIC RECORDS SECTION Spring 2016 series on processing digital materials.

@book{dunham_processing_2016,
	title = {Processing {Digital} {Research} {Data}},
	url = {https://saaers.wordpress.com/2016/05/11/processing-digital-research-data/},
	abstract = {This is the sixth post in SAA'S ELECTRONIC RECORDS SECTION Spring 2016 series on processing digital materials.},
	author = {Dunham, Elise},
	year = {2016},
	note = {Publication Title: BLOGGERS!
Type: THE BLOG OF SAA'S ELECTRONIC RECORDS SECTION},
}

This is the sixth post in SAA'S ELECTRONIC RECORDS SECTION Spring 2016 series on processing digital materials.

@book{drake_radtech_2016,
	address = {Cambridge, MA},
	title = {{RadTech} {Meets} {RadArch}: {Towards} {A} {New} {Principle} for {Archives} and {Archival} {Description}},
	url = {https://medium.com/on-archivy/radtech-meets-radarch-towards-a-new-principle-for-archives-and-archival-description-568f133e4325},
	abstract = {This talk, which formed part of a panel about archival description, was delivered at the 2016 Radcliffe Workshop on Technology \& Archival Processing, held on April 4–5, 2016, in Cambridge, MA. The panel, moderated by Jennifer Weintraub, also featured Anne Wootton and Kari Smith.},
	author = {Drake, Jarrett},
	year = {2016},
}

This talk, which formed part of a panel about archival description, was delivered at the 2016 Radcliffe Workshop on Technology & Archival Processing, held on April 4–5, 2016, in Cambridge, MA. The panel, moderated by Jennifer Weintraub, also featured Anne Wootton and Kari Smith.

@article{prael_getting_2015,
	title = {Getting to {Know} {FRED}: {Introducing} {Workflows} for {Born}-{Digital} {Content}},
	shorttitle = {Getting to {Know} {FRED}},
	url = {http://hdl.handle.net/1903/16384},
	doi = {10.13016/M2D91V},
	language = {en},
	urldate = {2020-09-08},
	author = {Prael, Alice and Wickner, Amy},
	year = {2015},
	note = {Publisher: Digital Repository at the University of Maryland},
	keywords = {FRED, Forensic Recovery of Evidence Device, born digital, poster, workflows},
}

@misc{coates_proceedings_2014,
	title = {Proceedings of the 11th {International} {Conference} on {Preservation} of {Digital} {Objects} {iPRES} 2014 ; {Melbourne}, 6-10 {October}},
	language = {English},
	publisher = {State Library of Victoria},
	author = {Coates, Serena and {International Conference on Preservation of Digital Objects} and {IPRES}},
	year = {2014},
	note = {ISBN: 9780642278814
Place: Melbourne
OCLC: 931751179},
}

@article{cocciolo_unix_2014,
	title = {Unix {Commands} and {Batch} {Processing} for the {Reluctant} {Librarian} or {Archivist}},
	url = {http://journal.code4lib.org/articles/9158},
	abstract = {The Unix environment offers librarians and archivists high-quality tools for quickly transforming born-digital and digitized assets, such as resizing videos, creating access copies of digitized photos, and making fair-use reproductions of audio recordings. These tools, such as ffmpeg, lame, sox, and ImageMagick, can apply one or more manipulations to digital assets without the need to manually process individual items, which can be error prone, time consuming, and tedious. This article will provide information on getting started in using the Unix environment to take advantage of these tools for batch processing.},
	language = {English},
	number = {23},
	journal = {Code4Lib Journal},
	author = {Cocciolo, Anthony},
	month = jan,
	year = {2014},
	keywords = {Command Line, Software/Tools, Unix},
}

The Unix environment offers librarians and archivists high-quality tools for quickly transforming born-digital and digitized assets, such as resizing videos, creating access copies of digitized photos, and making fair-use reproductions of audio recordings. These tools, such as ffmpeg, lame, sox, and ImageMagick, can apply one or more manipulations to digital assets without the need to manually process individual items, which can be error prone, time consuming, and tedious. This article will provide information on getting started in using the Unix environment to take advantage of these tools for batch processing.

@incollection{light_managing_2014,
	title = {Managing {Risk} with a {Virtual} {Reading} {Room}: {Two} {Born} {Digital} {Projects}},
	url = {http://digitalscholarship.unlv.edu/lib_articles/463/},
	abstract = {In March 2010, the University of California, Irvine, launched a site to provide online access to papers of Richard Rorty in the form of a virtual reading room.1 Although we didn’t know it then, we quickly learned that we were one of the first academic repositories in the United States to risk providing remote, online access to born-digital manuscripts. The virtual reading room mitigated the risks involved in providing this kind of access to personal, archival materials with privacy and copyright issues by limiting the number of qualified users and by limiting the discoverability of full-text content on the open web. In January 2013, we launched a site providing access to another group of born-digital materials, the papers of Mark Poster. The two collections had as many differences as they did commonalities, and a comparison of the two projects is useful for understanding the range of decisions and issues that ultimately impact access to born-digital personal manuscript collections.},
	booktitle = {Reference and {Access} {Innovative} {Practices} for {Archives} and {Special} {Collections}},
	publisher = {Rowman \& Littlefield Publishers},
	author = {Light, Michelle},
	year = {2014},
}

In March 2010, the University of California, Irvine, launched a site to provide online access to papers of Richard Rorty in the form of a virtual reading room.1 Although we didn’t know it then, we quickly learned that we were one of the first academic repositories in the United States to risk providing remote, online access to born-digital manuscripts. The virtual reading room mitigated the risks involved in providing this kind of access to personal, archival materials with privacy and copyright issues by limiting the number of qualified users and by limiting the discoverability of full-text content on the open web. In January 2013, we launched a site providing access to another group of born-digital materials, the papers of Mark Poster. The two collections had as many differences as they did commonalities, and a comparison of the two projects is useful for understanding the range of decisions and issues that ultimately impact access to born-digital personal manuscript collections.

@book{dorpinghaus_metadata_2014,
	address = {Washington, D.C.},
	title = {Metadata and {Digital} {Preservation}: {How} {Much} do we {Really} {Need}?},
	url = {http://archivists.org/2014/schedule/sessions#.WA_Jp_krJhF},
	abstract = {Digital objects include both files and accompanying metadata, but how much and which metadata are actually necessary to preserve and provide long-term access? Panelists examine tradeoffs related to what metadata to include in the Archival Information Package. The challenges of applying different schemas to metadata from a variety of sources, deciding which PREMIS metadata are essential, and merging file/folder-based descriptions with item-level systems also are explored.},
	author = {Dorpinghaus, Sarah and Eubank, Kelly and Evans, Mark and Goethals, Andrea},
	year = {2014},
}

Digital objects include both files and accompanying metadata, but how much and which metadata are actually necessary to preserve and provide long-term access? Panelists examine tradeoffs related to what metadata to include in the Archival Information Package. The challenges of applying different schemas to metadata from a variety of sources, deciding which PREMIS metadata are essential, and merging file/folder-based descriptions with item-level systems also are explored.

@book{callahan_value_2014,
	title = {The {Value} of {Archival} {Description}, {Considered}},
	url = {https://icantiemyownshoes.wordpress.com/2014/04/04/the-value-of-archival-description-considered/},
	abstract = {In their initial email, Ellen Shea and Mary O’Connell Murphy asked, “Is the product of a finding aid worthy of the time required to make them considering emerging technologies? Where do you think research guides might be headed in the future? How do you think they must change in order to improve access to archival collections and meet today’s user’s needs?” Most provocatively, they asked, “What do researchers really want from finding aids? Do they want them at all?” And I think that the answer is no. And maybe. And yes.In their initial email, Ellen Shea and Mary O’Connell Murphy asked, “Is the product of a finding aid worthy of the time required to make them considering emerging technologies? Where do you think research guides might be headed in the future? How do you think they must change in order to improve access to archival collections and meet today’s user’s needs?” Most provocatively, they asked, “What do researchers really want from finding aids? Do they want them at all?” And I think that the answer is no. And maybe. And yes.},
	language = {English},
	author = {Callahan, Maureen},
	year = {2014},
	note = {Publication Title: Chaos –{\textbackslash}textgreater Order
Type: Blog},
}

In their initial email, Ellen Shea and Mary O’Connell Murphy asked, “Is the product of a finding aid worthy of the time required to make them considering emerging technologies? Where do you think research guides might be headed in the future? How do you think they must change in order to improve access to archival collections and meet today’s user’s needs?” Most provocatively, they asked, “What do researchers really want from finding aids? Do they want them at all?” And I think that the answer is no. And maybe. And yes.In their initial email, Ellen Shea and Mary O’Connell Murphy asked, “Is the product of a finding aid worthy of the time required to make them considering emerging technologies? Where do you think research guides might be headed in the future? How do you think they must change in order to improve access to archival collections and meet today’s user’s needs?” Most provocatively, they asked, “What do researchers really want from finding aids? Do they want them at all?” And I think that the answer is no. And maybe. And yes.

@article{endredy_more_2013,
	title = {More {Effective} {Boilerplate} {Removal} - the {GoldMiner} {Algorithm}},
	issn = {1870-9044},
	url = {http://polibits.gelbukh.com/2013_48},
	language = {eng},
	number = {48},
	journal = {Polibits - Research journal on Computer science and computer engineering with applications},
	author = {Endrédy, István and Novák, Attila},
	year = {2013},
	keywords = {Corpus building, boilerplate removal, the web as corpus},
	pages = {79--83},
}

@article{zhang_original_2012,
	title = {Original {Order} in {Digital} {Archives}},
	volume = {74},
	copyright = {Copyright (c)},
	issn = {1923-6409},
	url = {http://journals.sfu.ca/archivar/index.php/archivaria/article/view/13410},
	abstract = {This article reports on the findings of a two-year study designed to investigate the validity of the principle of original order when electronic records are transferred from recordkeeping systems and processed into digital archives. Guided by a knowledge framework identified from archival literature, the author conducted case studies of three digital archival projects to explore the definitions, purposes, and representations of original order witnessed in digital archives. The findings of the study demonstrate a variety of structures and relationships of records created electronically and identified and preserved as such in digital archives, and highlight the possibilities and challenges archivists face in digital archival representation.RÉSUMÉ Cet article fait état des résultats d’une étude de deux ans qui visait à établir la validité du principe de l’ordre original lorsque des documents électroniques sont transférés des systèmes de gestion de l’information et traités comme archives numériques. En se servant d’un cadre de connaissances établi à partir des écrits en archivistique, l’auteure a mené des études de cas de trois projets d’archives numériques afin d’explorer les définitions, les buts et les représentations de l’ordre original tels qu’elle les a perçus dans les archives numériques. Les résultats de cette étude montrent une variété de structures et de liens entre les documents créés électroniquement, puis identifiés et conservés en tant que tel dans les archives numériques. L’étude met en évidence les possibilités et les défis auxquels font face les archivistes en ce qui concerne la représentation de l’archivage numérique.},
	language = {en},
	number = {0},
	journal = {Archivaria},
	author = {Zhang, Jane},
	year = {2012},
}

This article reports on the findings of a two-year study designed to investigate the validity of the principle of original order when electronic records are transferred from recordkeeping systems and processed into digital archives. Guided by a knowledge framework identified from archival literature, the author conducted case studies of three digital archival projects to explore the definitions, purposes, and representations of original order witnessed in digital archives. The findings of the study demonstrate a variety of structures and relationships of records created electronically and identified and preserved as such in digital archives, and highlight the possibilities and challenges archivists face in digital archival representation.RÉSUMÉ Cet article fait état des résultats d’une étude de deux ans qui visait à établir la validité du principe de l’ordre original lorsque des documents électroniques sont transférés des systèmes de gestion de l’information et traités comme archives numériques. En se servant d’un cadre de connaissances établi à partir des écrits en archivistique, l’auteure a mené des études de cas de trois projets d’archives numériques afin d’explorer les définitions, les buts et les représentations de l’ordre original tels qu’elle les a perçus dans les archives numériques. Les résultats de cette étude montrent une variété de structures et de liens entre les documents créés électroniquement, puis identifiés et conservés en tant que tel dans les archives numériques. L’étude met en évidence les possibilités et les défis auxquels font face les archivistes en ce qui concerne la représentation de l’archivage numérique.

@book{huebscher_no_2012,
	address = {San Diego, CA},
	title = {No {Time} to {Waste}: {Moving} the {Pawlenty} {Digital} {Records} from {Appraisal} to {MPLP} {Online} {Access}},
	url = {http://saa.archivists.org/4DCGI/events/eventdetail.html?Action=Events_Detail&&InvID_W=2337},
	author = {Huebscher, Jennifer},
	month = aug,
	year = {2012},
}

@book{phillips_more_2012,
	title = {More {Product}, {Less} {Process} for {Born}-{Digital} {Collections}: {Reflections} on {CurateCamp} {Processing}},
	url = {http://blogs.loc.gov/thesignal/2012/08/more-product-less-process-for-born-digital-collections-reflections-on-curatecamp-processing/},
	abstract = {“What’s the bare minimum I can responsibly do with my electronic stuff?” was one of the central questions on the table at CurateCamp Processing. The unconference, focused on Processing Data / Processing Collections, was a great way for a group of thought leaders and practitioners to surface issues keeping them up at night, compare notes, and start charting a path forward. The theme for this CURATEcamp framed a series of discussions on how archivists and librarians think about processing digital collections compared to the ways programmers, software developers, and engineers think about processing data. We worked on a lot of different issues, but I found one particularly interesting: what do recent discussions in the archival community about minimal processing mean for digital materials?},
	author = {Phillips, Meg},
	month = aug,
	year = {2012},
	note = {Publication Title: The Signal
Type: Library of Congress' Digital Preservation Blog},
}

“What’s the bare minimum I can responsibly do with my electronic stuff?” was one of the central questions on the table at CurateCamp Processing. The unconference, focused on Processing Data / Processing Collections, was a great way for a group of thought leaders and practitioners to surface issues keeping them up at night, compare notes, and start charting a path forward. The theme for this CURATEcamp framed a series of discussions on how archivists and librarians think about processing digital collections compared to the ways programmers, software developers, and engineers think about processing data. We worked on a lot of different issues, but I found one particularly interesting: what do recent discussions in the archival community about minimal processing mean for digital materials?

@book{kirschenbaum_digital_2010,
	address = {Washington, D.C},
	series = {{CLIR} publication},
	title = {Digital forensics and born-digital content in cultural heritage collections},
	isbn = {978-1-932326-37-6},
	number = {no. 149},
	publisher = {Council on Library and Information Resources},
	author = {Kirschenbaum, Matthew G. and Ovenden, Richard and Redwine, Gabriela and Donahue, Rachel},
	year = {2010},
	keywords = {Administration, Administration Technological innovations, Archives, Data processing, Digital forensic science, Digital humanities, Digital preservation, Electronic records, Forensic sciences, Management},
}

@book{society_for_imaging_science_and_technology_archiving_2009,
	address = {Springfield, Va},
	title = {Archiving 2009: {May} 4 - 7, 2009, {Arlington}, {Va}. ; preservation strategies and imaging technologies for cultural heritage institutions and memory organizations ; final program and proceedings ; [{Sixth} {Annual} {Archiving} {Conference}]},
	isbn = {978-0-89208-284-1},
	shorttitle = {Archiving 2009},
	language = {eng},
	publisher = {Soc. for Imaging Science and Technology},
	editor = {Society for Imaging Science {and} Technology},
	year = {2009},
}

@inproceedings{gollins_parsimonious_2009,
	title = {Parsimonious preservation: preventing pointless processes!},
	url = {http://www.nationalarchives.gov.uk/documents/information-management/parsimonious-preservation.pdf},
	abstract = {While there are many and varied threats to the successful curation of digital material, the impression given by the current generation of digital preservation systems and by much of the “received wisdom” in the digital preservation community is that imminent technological (software/data format) obsolescence is the primary threat. This gives rise to the belief that the only way to successfully start doing digital preservation is to invest in a technically complex, expensive, and difficult to operate integrated digital preservation system. This paper argues that, while the threat of technological obsolescence is real in some particular cases, a much more imminent threat is poor capture and inability to achieve safe and secure storage of the original material. By applying the principle of parsimony to digital preservation, institutions can find ways forward that are incremental, manageable and affordable, and which achieve the goal of securing our digital heritage for the next generation. The paper observes that many existing institutional IT systems (and their support teams) provide as a part of normal business the capability to address many of the challenges of capture, custody, and integrity facing the new digital curator. The paper also argues that open source or free resources can be applied intelligently to further address these challenges, without needing huge integration or significant IT resource allocation. The paper gives an example of this and argues that the simplicity of a digital preservation system itself is critical to ensuring the long term access to the material that it holds. This approach makes it possible for even the smallest institution to begin to take steps to ensure the long-term survival of our vital digital heritage.},
	author = {Gollins, Tim},
	year = {2009},
	keywords = {Case study, Government, Software/Tools},
}

While there are many and varied threats to the successful curation of digital material, the impression given by the current generation of digital preservation systems and by much of the “received wisdom” in the digital preservation community is that imminent technological (software/data format) obsolescence is the primary threat. This gives rise to the belief that the only way to successfully start doing digital preservation is to invest in a technically complex, expensive, and difficult to operate integrated digital preservation system. This paper argues that, while the threat of technological obsolescence is real in some particular cases, a much more imminent threat is poor capture and inability to achieve safe and secure storage of the original material. By applying the principle of parsimony to digital preservation, institutions can find ways forward that are incremental, manageable and affordable, and which achieve the goal of securing our digital heritage for the next generation. The paper observes that many existing institutional IT systems (and their support teams) provide as a part of normal business the capability to address many of the challenges of capture, custody, and integrity facing the new digital curator. The paper also argues that open source or free resources can be applied intelligently to further address these challenges, without needing huge integration or significant IT resource allocation. The paper gives an example of this and argues that the simplicity of a digital preservation system itself is critical to ensuring the long term access to the material that it holds. This approach makes it possible for even the smallest institution to begin to take steps to ensure the long-term survival of our vital digital heritage.

@techreport{schaffner_metadata_2009,
	title = {The {Metadata} is the {Interface}: {Better} {Description} for {Better} {Discovery} of {Archives} and {Special} {Collections}, {Synthesized} from {User} {Studies}},
	url = {http://www.oclc.org/programs/publications/reports/2009-06.pdf},
	institution = {OCLC},
	author = {Schaffner, Jennifer},
	year = {2009},
	keywords = {Metadata},
	pages = {18},
}

@article{king_introduction_2007,
	title = {An {Introduction} to the {Dataverse} {Network} as an {Infrastructure} for {Data} {Sharing}},
	volume = {36},
	url = {http://gking.harvard.edu/files/gking/files/dvn.pdf},
	journal = {Sociological Methods and Research},
	author = {King, Gary},
	year = {2007},
	pages = {173--199},
}

@techreport{underwood_perpos_2007,
	title = {{PERPOS}: {An} {Electronic} {Records} {Repository} and {Archival} {Processing} {System}},
	url = {https://ils.unc.edu/digccurr2007/papers/underwood_paper_6-3.pdf},
	abstract = {An Electronic Records Repository and an Archival Processing System have been developed to support archivists in processing Presidential e-records. Accession, arrangement, preservation, review, description, and creation of finding aids are supported. The data management system includes the schema for the repository as well as metadata for arrangement, review, preservation and description. The prototype system provides an environment for the experimental application of advanced information technologies to archival processes.},
	author = {Underwood, William and Laib, Sandra},
	year = {2007},
}

An Electronic Records Repository and an Archival Processing System have been developed to support archivists in processing Presidential e-records. Accession, arrangement, preservation, review, description, and creation of finding aids are supported. The data management system includes the schema for the repository as well as metadata for arrangement, review, preservation and description. The prototype system provides an environment for the experimental application of advanced information technologies to archival processes.

@article{peters_when_2006,
	title = {When {Not} {All} {Papers} are {Paper}: {A} {Case} {Study} in {Digital} {Archivy}},
	volume = {24},
	url = {http://digitalcommons.kennesaw.edu/provenance/vol24/iss1/3},
	abstract = {Hypertext poet Deena Larsen is worried about the potential loss of her digital poetry, but she has a plan to save it. In a 2004 article, “The Uncertain Fate of Scholarly Artifacts in a Digital Age,” Larsen revealed her plans for preserving her hypertext work Marble Springs. “Ms. Larsen started collecting old Macintosh computers so people will always be able to read Marble Springsin its original format. She has 100 computers in her two-bedroom apartment.” Although Larsen’s two-bedroom mausoleum of circa 1990s technology is one strategy for saving born-digital hypertext works, it is probably not the best. An armada of aging hardware will not protect digital objects from hard drive crashes, hardware failure, inoperable software, operating system malfunctions, unreadability, or natural disasters. Preservation of electronic records requires a commitment to active preservation practices including migration, refreshing, and integrity and authenticity checks of stored digital records. Maintaining the status quo, regardless of the magnitude of hardware and software stockpiles, is not a viable preservation strategy. The Electronic Literature Organization (ELO) notes the inadequacy of just holding onto digital materials and advocates more active digital preservation strategies in their latest publication, Born- Again Bits: “The stakes are even higher when we consider that keeping works of electronic literature alive in their original form does not serve all present needs, let alone those of the future.”},
	number = {1},
	journal = {Provenance, Journal of the Society of Georgia Archivists},
	author = {Peters, Catherine Stollar},
	month = jan,
	year = {2006},
	keywords = {Arrangement, Case study, Description, Metadata, Software/Tools},
	pages = {22--34},
}

Hypertext poet Deena Larsen is worried about the potential loss of her digital poetry, but she has a plan to save it. In a 2004 article, “The Uncertain Fate of Scholarly Artifacts in a Digital Age,” Larsen revealed her plans for preserving her hypertext work Marble Springs. “Ms. Larsen started collecting old Macintosh computers so people will always be able to read Marble Springsin its original format. She has 100 computers in her two-bedroom apartment.” Although Larsen’s two-bedroom mausoleum of circa 1990s technology is one strategy for saving born-digital hypertext works, it is probably not the best. An armada of aging hardware will not protect digital objects from hard drive crashes, hardware failure, inoperable software, operating system malfunctions, unreadability, or natural disasters. Preservation of electronic records requires a commitment to active preservation practices including migration, refreshing, and integrity and authenticity checks of stored digital records. Maintaining the status quo, regardless of the magnitude of hardware and software stockpiles, is not a viable preservation strategy. The Electronic Literature Organization (ELO) notes the inadequacy of just holding onto digital materials and advocates more active digital preservation strategies in their latest publication, Born- Again Bits: “The stakes are even higher when we consider that keeping works of electronic literature alive in their original form does not serve all present needs, let alone those of the future.”

@inproceedings{pearce-moses_new_2006,
	address = {Washington, DC},
	title = {New {Skills} for a {Digital} {Era}},
	url = {http://www.archivists.org/publications/proceedings/NewSkillsForADigitalEra.pdf},
	publisher = {Society of American Archivists},
	editor = {Pearce-Moses, Richard and Davis, Susan E.},
	year = {2006},
	keywords = {Core Texts},
}

@article{rosenthal_requirements_2005,
	title = {Requirements for {Digital} {Preservation} {Systems}: {A} {Bottom}-{Up} {Approach}},
	volume = {11},
	issn = {1082-9873},
	shorttitle = {Requirements for {Digital} {Preservation} {Systems}},
	url = {http://www.dlib.org/dlib/november05/rosenthal/11rosenthal.html},
	doi = {10.1045/november2005-rosenthal},
	language = {en},
	number = {11},
	urldate = {2022-06-15},
	journal = {D-Lib Magazine},
	author = {Rosenthal, David S. H. and Robertson, Thomas and Lipkis, Tom and Reich, Vicky and Morabito, Seth},
	month = nov,
	year = {2005},
}

@book{project_paradigm_2005,
	title = {{PARADIGM}: {Workbook} on {Digital} {Private} {Papers}},
	copyright = {Creative Commons Attribution-Share Alike 2.0 UK: England \& Wales License},
	url = {http://www.paradigm.ac.uk/index.html},
	abstract = {The workbook will detail the experiences of the [PARADIGM] project, outline best practice as identified through project staff working on the Project itself, comparing experience with other digital preservation activities, and through maintaining currency with the literature and best practice globally, through close liaison with groups such as the Digital Preservation Coalition.},
	author = {Project, PARADIGM},
	year = {2005},
	note = {Publication Title: PARADIGM},
	keywords = {Standards/best practices, Workflows},
}

The workbook will detail the experiences of the [PARADIGM] project, outline best practice as identified through project staff working on the Project itself, comparing experience with other digital preservation activities, and through maintaining currency with the literature and best practice globally, through close liaison with groups such as the Digital Preservation Coalition.

@inproceedings{garrett_producer-archive_2004,
	address = {Montreal, Quebec, Canada},
	title = {The {Producer}-{Archive} {Interface} {Methodology} {Abstract} {Standard} ({PAIMAS})},
	url = {https://arc.aiaa.org/doi/10.2514/6.2004-649-446},
	doi = {10.2514/6.2004-649-446},
	language = {en},
	urldate = {2021-06-15},
	booktitle = {Space {OPS} 2004 {Conference}},
	publisher = {American Institute of Aeronautics and Astronautics},
	author = {Garrett, J.G.},
	month = may,
	year = {2004},
}

@book{ccsds_reference_2002,
	title = {Reference {Model} for an {Open} {Archival} {Information} {System} ({OAIS}), {Magenta} {Book}},
	url = {http://public.ccsds.org/publications/archive/650x0b1.pdf},
	publisher = {CCSDS - Consultative Committee for Space Data Systems},
	author = {{CCSDS}},
	month = jan,
	year = {2002},
	keywords = {OAIS Referenzmodell reference.model},
}

@misc{noauthor_cca_nodate,
	title = {{CCA} {Digital} {Archives} {Processing} {Manual}},
	url = {https://github.com/CCA-Public/digital-archives-manual},
}

@misc{noauthor_born-digital_nodate,
	title = {Born-digital {Accession} and {Ingest} {Procedure} {Manual}},
	url = {https://austinlibrary.com/ahc/downloads/Born_Digital_Processing_Manual.pdf},
}

@misc{odouk_ima_born_nodate,
	title = {Born {Digital} {Processing} and {Preservation} {Collaborative} {Project}},
	url = {https://www.tdl.org/2024/05/born-digital-processing-and-preservation-collaborative-project/},
	author = {Odouk, Ima},
}

@misc{kozlony_342016_nodate,
	title = {34/2016. ({XI}. 30.) {EMMI} rendelet az elektronikus formában tárolt iratok közlevéltári átvételének eljárásrendjéről és műszaki követelményeiről},
	url = {https://magyarkozlony.hu/dokumentumok/afc7a7bc8a8b8c9e22db85179ec5932bc5fa05e9/megtekintes},
	urldate = {2021-06-15},
	author = {Közlöny, Magyar},
}

@misc{noauthor_using_nodate,
	title = {Using {PDF}/{A} as a {Preservation} {Format}},
	url = {http://www.archives.nysed.gov/records/mr_advisories_pdfa.shtml},
	abstract = {What is PDF/A?The PDF/A (or Portable Document Format Archival) is a format designed as a preservation format for digital records, particularly documents. The format, though, can also be used for scanned documents. It is an international standard and a subset of the PDF format. One of the great values of PDF formats is that they are open standards, used widely across the world,},
	language = {en},
	urldate = {2021-04-13},
	journal = {New York State Archives},
}

What is PDF/A?The PDF/A (or Portable Document Format Archival) is a format designed as a preservation format for digital records, particularly documents. The format, though, can also be used for scanned documents. It is an international standard and a subset of the PDF format. One of the great values of PDF formats is that they are open standards, used widely across the world,

@misc{noauthor_archives_nodate,
	title = {Archives and {Manuscripts}},
	url = {https://www.tandfonline.com/toc/raam20/47/3},
}