Archives and AI: An Overview of Current Debates and Future Perspectives
Open accessThe DOI matches its Crossref record; 66 of the 67 references it cites were found in a registry or an index; none of the 14 sources its claims cite is checked for support yet.
Abstract
The digital transformation is turning archives, both old and new, into data. As a consequence, automation in the form of artificial intelligence techniques is increasingly applied both to scale traditional recordkeeping activities, and to experiment with novel ways to capture, organise, and access records. We survey recent developments at the intersection of Artificial Intelligence and archival thinking and practice. Our overview of this growing body of literature is organised through the lenses of the Records Continuum model. We find four broad themes in the literature on archives and artificial intelligence: theoretical and professional considerations, the automation of recordkeeping processes, organising and accessing archives, and novel forms of digital archives. We conclude by underlining emerging trends and directions for future work, which include the application of recordkeeping principles to the very data and processes that power modern artificial intelligence and a more structural—yet critically aware—integration of artificial intelligence into archival systems and practice.
Overview
CoChat Summary
TL;DR
This survey reviews literature at the intersection of AI and archives/recordkeeping, organising 53 references through the Records Continuum model into four broad themes. It finds AI increasingly applied across archival processes, with most work on organising/accessing and pluralising, less on capture, minimal on creation, and calls for more critical, interdisciplinary integration and for recordkeeping principles to inform AI.
Key findings
- The survey identifies four broad themes: theoretical and professional considerations; automation of recordkeeping processes; organising and accessing archives; and novel forms of digital archives.
- Across the 53 references, a large share of work focuses on the “organise” and “pluralise” dimensions of the Records Continuum, to a lesser degree on “capture,” and to a minimal degree on “create.”
- AI is discussed for automating appraisal, handling sensitive information, metadata creation, content extraction/indexation, distant reading, search and retrieval, and novel born-digital archives; examples include Transkribus, topic modelling, ePADD, and entity-based indexation.
- Emerging trends include applying recordkeeping principles to the data and processes powering modern AI, and a more structural yet critically aware integration of AI into archival systems and practice.
Methods
- The authors compiled a list of publication venues in archive and information science and digital humanities, sifted all issues from 2015 to 2020, and selected contributions with a direct or explicit reference to recordkeeping theory and practice and to AI.
- They used selected publications as seeds for reference and citation lookup, then added key recent references from outside the original venues, resulting in 53 references analysed.
- The literature was organised and discussed using the Records Continuum model; the authors state this is not a systematic review but a representative overview.
Limitations
- The authors state that the work is not a systematic review but a representative overview, and they acknowledge the influence of their own perspectives on the selection.
- The authors state that their venue list is limited and excludes domains such as law, policing and surveillance, and document processing; they also excluded purely technical work on archival materials without archival reflection and archival work without explicit reference to AI.
- The authors state that the survey leaves out key related areas including AI and law and the ethics of AI; the text also makes evident that coverage is time-bounded to 2015–2020 and non-exhaustive.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 8 Not valid · 15 Not checked · 55 Own results and interpretations
In the paper
“Manual, high-quality, and collaborative data curation remains a successful approach in some instances [Turchin 2015].”
§ Archives and AI: An Overview of Current Debates and Future Perspectives > 3.2 Automating Recordkeeping Processes and Decisions
What the sources say
- Not matchedcites Turchin 2015
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“To our knowledge, there is no such survey of the relationship between AI and archives.”
§ Archives and AI: An Overview of Current Debates and Future Perspectives > 1 INTRODUCTION
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find four broad themes in the literature on archives and artificial intelligence: theoretical and professional considerations, the automation of recordkeeping processes, organising and accessing archives, and novel forms of digital archives.”
§ Archives and AI: An Overview of Current Debates and Future Perspectives > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In other cases, AI technologies and methods are propagated for analysing the new, vast collections of born digital records that emerge both within and outside established archival institutions.”
§ Archives and AI: An Overview of Current Debates and Future Perspectives > 5 NOVEL FORMS OF DIGITAL ARCHIVES
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“AI is primarily used to automate processes in existing archives, e.g., after their digitisation or when born-digital, and to improve their accessibility.”
§ Archives and AI: An Overview of Current Debates and Future Perspectives > 6 DISCUSSION
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
10 more claims
Create a free account to see all 78 claims and every source verdict.
- Probably not a substantial claim. 56
- It may state two separate claims as one. 12
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“A recent literature review has divided AI applications in archives according to their role in the creation, capture, organize, and pluralize stages of a record's life under the records continuum model [ 15 , 60 ].”
From Positioning Paradata: A Conceptual Frame for AI Processual Documentation in Archives and Recordkeeping Contexts (2023) · cites this paper as [15]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence
Mohamed, S., Png, M.-T., & Isaac, W. (2020) · Philosophy & Technology · doi:10.1007/s13347-020-00405-8 · Cited by 912
Machine Learning for Cultural Heritage: A Survey
Fiorucci, M., Khoroshiltseva, M., Pontil, M., Traviglia, A., Del Bue, A., & James, S. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.02.017 · Cited by 365
2017 IEEE International Conference on Big Data (Big Data)
(2017) · doi:10.1109/bigdata41644.2017 · Cited by 302
Lessons from archives: strategies for collecting sociocultural data in machine learning
Jo, E. S., & Gebru, T. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372829 · Cited by 240
Document Layout Analysis: A Comprehensive Survey
Binmakhashen, G. M., & Mahmoud, S. A. (2020) · ACM Computing Surveys · doi:10.1145/3355610 · Cited by 183
Bode, K. (2017) · Modern Language Quarterly · doi:10.1215/00267929-3699787 · Cited by 127
Muehlberger, G., Seaward, L., Terras, M., Ares Oliveira, S., Bosch, V., Bryan, M., Colutto, S., Déjean, H., Diem, M., Fiel, S., et al. (2019) · Journal of Documentation · doi:10.1108/jd-07-2018-0114 · Cited by 108
Lost in the Infinite Archive: The Promise and Pitfalls of Web Archives
Milligan, I. (2016) · International Journal of Humanities and Arts Computing · doi:10.3366/ijhac.2016.0161 · Cited by 104
The visual digital turn: Using neural networks to study historical images
Wevers, M., & Smits, T. (2019) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqy085 · Cited by 104
Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine LearningPreprint
Jo, E. S., & Gebru, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.10389 · Cited by 102
State of the Field: Digital History
Romein, C. A., Kemman, M., Birkholz, J. M., Baker, J., de Gruijter, M., Meroño-Peñuela, A., Ries, T., Ros, R., & Scagliola, S. (2020) · History · doi:10.1111/1468-229x.12969 · Cited by 83
More human than human? Artificial intelligence in the archive
Rolan, G., Humphries, G., Jeffrey, L. K., Samaras, E., Antsoupova, T., & Stuart, K. (2018) · Archives and Manuscripts · doi:10.1080/01576895.2018.1502088 · Cited by 77
Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020
(2020) · doi:10.1145/3383583 · Cited by 70
Archival Records and Training in the Age of Big Data
Marciano, R. J., Lemieux, V. L., Hedges, M., Esteva, M., Underwood, W., Kurtz, M. J., & Conrad, M. (2018) · Emerald Group Publishing Limited eBooks · doi:10.1108/s0065-28302018000044b010 · Cited by 68 · cited 1×
“This dialogue is reflected in an emerging field that has been labelled as Computational Archival Science [Lemieux 2018; Marciano 2018].”
Ruest, N., Lin, J., Milligan, I., & Fritz, S. (2020) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3383583.3398513 · Cited by 52
Moretti, G., Sprugnoli, R., Menini, S., & Tonelli, S. (2016) · Knowledge-Based Systems · doi:10.1016/j.knosys.2016.08.003 · Cited by 50
The Reconfiguration of the Archive as Data to Be Mined
Moss, M., Thomas, D. R., & Gollins, T. (2018) · Archivaria · Cited by 42
Natural language processing and machine learning as practical toolsets for archival processing
Hutchinson, T. (2020) · Records Management Journal · doi:10.1108/rmj-09-2019-0055 · Cited by 42
Hinrichs, U., Alex, B., Clifford, J., Watson, A., Quigley, A. J., Klein, E., & Coates, C. M. (2015) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqv046 · Cited by 41
Black, M. L. (2016) · International Journal of Humanities and Arts Computing · doi:10.3366/ijhac.2016.0162 · Cited by 36
Seshat: The Global History Databank
Turchin, P., Brennan, R., Currie, T., Feeney, K., Francois, P., Hoyer, D., Manning, J., Marciniak, A., Mullins, D., Palmisano, A., et al. (2015) · Cliodynamics: The Journal of Quantitative History and Cultural Evolution · doi:10.21237/c7clio6127917 · Cited by 35
Stewardship in the "Age of Algorithms"
Lynch, C. (2017) · First Monday · doi:10.5210/fm.v22i12.8097 · Cited by 33
Bunn, J. (2020) · Records Management Journal · doi:10.1108/rmj-08-2019-0038 · Cited by 33
Appraising, processing, and providing access to email in contemporary literary archives
Schneider, J., Adams, C., DeBauche, S., et al. (2019) · Archives and Manuscripts · doi:10.1080/01576895.2019.1622138 · Cited by 30
Conceptualizing 21st-Century Archives
Gilliland, A. J. (2017) · Cited by 26
Assisting the appraisal of e-mail records with automatic classification
Vellino, A., & Alberts, I. (2016) · Records Management Journal · doi:10.1108/rmj-02-2016-0006 · Cited by 26
Critical Search: A Procedure for Guided Reading in Large-Scale Textual Corpora
Guldi, J. (2018) · Journal of Cultural Analytics · doi:10.22148/16.030 · Cited by 23
Negotiating the born-digital: a problem of search
Winters, J., & Prescott, A. (2019) · Archives and Manuscripts · doi:10.1080/01576895.2019.1640753 · Cited by 22
Computer-Assisted Appraisal and Selection of Archival Materials
Lee, C. A. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622267 · Cited by 21 · cited 1×
“Lee [2018] observes some progress in applying software support in archival processes, but argues that much more could be achieved by deploying digital forensics, natural language processing, and machine learning in developing better support in the vital recordkeeping domain of appraisal and he…”
Shabou, B. M., Tièche, J., Knafou, J., et al. (2020) · Records Management Journal · doi:10.1108/rmj-09-2019-0049 · Cited by 21
Risi, J., Sharma, A., Shah, R., Connelly, M., & Watts, D. J. (2019) · Nature Human Behaviour · doi:10.1038/s41562-019-0620-8 · Cited by 21
Our Digital Legacy: an Archival Perspective
Moss, M., & Gollins, T. J. (2017) · Northumbria Research Link (Northumbria University) · Cited by 19
van den Heuvel, C. (2015) · International Journal of Humanities and Arts Computing · doi:10.3366/ijhac.2015.0140 · Cited by 17
Lawrence, D. R. (2017) · Cambridge Quarterly of Healthcare Ethics · doi:10.1017/s0963180116001158 · Cited by 17
Diplomatic documents data for international relations: the Freedom of Information Archive Database
Connelly, M., Hicks, R., Jervis, R. L., et al. (2020) · Conflict Management and Peace Science · doi:10.1177/0738894220930326 · Cited by 17
Towards Building a Political Protest Database to Explain Changes in the Welfare State
Sönmez, Ç., Özgür, A., & Yörük, E. (2016) · SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities · doi:10.18653/v1/w16-2113 · Cited by 16
Detecting and Characterizing Events
Chaney, A. J. B., Wallach, H., Connelly, M., & Blei, D. M. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1122 · Cited by 16 · cited 1×
“Chaney [2016] presents the “capsule” model for analysing historical corpora containing events, with a case study on the US State Department cables.”
Lee, B. C. G. (2018) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqy063 · Cited by 16 · cited 1×
“Lee [2019] uses visual template matching and automatic classification to retrieve reference cards from the International Tracing Service digital archive, one of the largest and most heterogeneous collections of Holocaust-related”
MethodIndex-Driven Digitization and Indexation of Historical Archives
Colavizza, G., Ehrmann, M., & Bortoluzzi, F. (2019) · Frontiers in Digital Humanities · doi:10.3389/fdigh.2019.00004 · Cited by 16
Self-citationTraces through time: A probabilistic approach to connected archival data
Ranade, S. (2016) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2016.7840983 · Cited by 15
History playground: A tool for discovering temporal trends in massive textual corpora
Lansdall-Welfare, T., & Cristianini, N. (2018) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqy077 · Cited by 14
It's the end of the archival profession as we know it, and I feel fine
Theimer, K. (2018) · Facet eBooks · doi:10.29085/9781783302192.002 · Cited by 13
Semantic Enrichment of a Multilingual Archive with Linked Open Data
Wilde, M. D., & Hengchen, S. (2018) · Digital Humanities Quarterly · doi:10.63744/eyh2pqnjmv7q · Cited by 12
Using Artificial Intelligence to Identify State SecretsPreprint
Souza, R. R., Coelho, F. C., Shah, R., & Connelly, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.00356 · Cited by 12
Conceptualizing 21st-century archives
Moss, M. (2015) · Archives and Records · doi:10.1080/23257962.2015.1010495 · Cited by 11
Chabin, M.-A. (2020) · Records Management Journal · doi:10.1108/rmj-08-2019-0042 · Cited by 11
Hengchen, S., Coeckelbergs, M., van Hooland, S., et al. (2016) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2016.7840981 · Cited by 10
Baron, J. R., & Payne, N. (2017) · doi:10.1109/cedem.2017.27 · Cited by 10
A discussion frame for explaining records that are based on algorithmic output
Andresen, H. (2019) · Records Management Journal · doi:10.1108/rmj-04-2019-0019 · Cited by 10
A record-keeping approach to managing IoT-data for government agencies
Sødring, T., Reinholdtsen, P., & Massey, D. (2020) · Records Management Journal · doi:10.1108/rmj-09-2019-0050 · Cited by 10 · cited 1×
“Based on two use cases (water-quality sensor data and automatic number plate recognition) Sødring [2020] argues that government agencies using such IoT systems should make sure that the way the resulting information is captured and organised complies with laws, regulations, and expectations…”
Protecting Privacy in the Archives: Supervised Machine Learning and Born-Digital Records
Hutchinson, T. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8621929 · Cited by 9 · cited 3×
“Hutchinson [2020] provides this perspective by giving an overview of efforts of using NLP and machine learning in appraisal. He reviews several software tools (among others, ePADD, BitCurator NLP, ArchExtract, and a few commercial tools) and identifies and discusses five design principles (usable, interoperable, flexi…”
BackgroundMethodBočytė, R., & Oomen, J. (2020) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0009188505060511 · Cited by 9
Recordkeeping Informatics for a Networked Age
Upward, F. H., Reed, B., Oliver, G., et al. (2020) · Figshare · doi:10.26180/5f3c6b5235336 · Cited by 8 · cited 3×
“Upward [2018] calls for a new discipline base that requires new professional groupings, new skills, and knowledge and concludes that “[t]he key to change lies with educators.””
InfluentialGupta, A., & Kapoor, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.04541 · Cited by 8
The future of archives as networked, decentralised, autonomous and global
Lemieux, V. (2018) · Archival Futures · doi:10.29085/9781783302192.004 · Cited by 8
From tree to network: reordering an archival catalogue
Bell, M. R. (2020) · Records Management Journal · doi:10.1108/rmj-09-2019-0051 · Cited by 7
Breaking down the invisible wall to enrich archival science and practice
Thibodeau, K. (2016) · 2016 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2016.7840986 · Cited by 6
Access technologies for the disruptive digital archive
Ranade, S. (2018) · Facet eBooks · doi:10.29085/9781783302192.007 · Cited by 6
Binary trees? Automatically identifying the links between born-digital records
Spencer, R. (2017) · Archives and Manuscripts · doi:10.1080/01576895.2017.1330158 · Cited by 5
Identifying epochs in text archives
Blanke, T., & WILSON, J. E. (2017) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2017.8258172 · Cited by 4
Self-citationIn-place Synchronisation of Hierarchical Archival Descriptions
Bryant, M., Reijnhoudt, L., & Simeonov, B. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622517 · Cited by 4 · cited 1×
“The project automatically synchronises archival metadata from several sources and complements them with user-generated metadata and thematic “virtual collections” [Bryant 2018].”
Metadata as a machine for feeling in Germaine Greer’s archive
Weber, M., & Buchanan, R. (2019) · Archives and Manuscripts · doi:10.1080/01576895.2019.1568266 · Cited by 3
Auto-classification in an international organization: report from a feasibility study
Büttner, G. (2019) · Comma · doi:10.3828/comma.2017.2.2 · Cited by 3
Coeckelbergs, M., & van Hooland, S. (2020) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-50072-6_4 · Cited by 3
Critical Search: A procedure for guided reading in large-scale textual corpora
Guldi, J. (2018) · Harvard Dataverse · doi:10.7910/dvn/bjnapd · Cited by 1
Hutchinson, T. (2017) · 2017 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2017.8258177
Research works printed but not linked: 2
- 10.5555/2999134.2999257 · doi:10.5555/2999134.2999257
- Moretti Franco. 2013. Distant Reading. Verso, London, New York.
Cited by
An Analysis of Research Trends for Using Artificial Intelligence in Cultural Heritage
Gîrbacia, F. (2024) · Electronics · doi:10.3390/electronics13183738 · Cited by 166
Artificial Intelligence for Digital Heritage Innovation: Setting up a R&D Agenda for Europe
Münster, S., Maiwald, F., di Lenardo, I., Henriksson, J., Isaac, A., Graf, M., Beck, C., & Oomen, J. (2024) · Heritage · doi:10.3390/heritage7020038 · Cited by 169
“Since data collection and suitable training data is an all-time challenge of AI, CH applications increase the complexity of gathering, annotating, and curating the data to create training sets for AI models taking into account specific CH aspects, e.g., time variance, digitized analog material, or…”
BackgroundDigital History and the Politics of Digitization
Zaagsma, G. (2022) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqac050 · Cited by 50
Cushing, A. L., & Osti, G. (2022) · Journal of Documentation · doi:10.1108/jd-08-2022-0170 · Cited by 71
Generative Ghosts: Anticipating Benefits and Risks of AI Afterlives
Morris, M. R., & Brubaker, J. R. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713758 · Cited by 138
“…HCI communities to design generative ghosts in a manner that mitigates risk, discuss the need to develop policies that protect values around privacy, consent, and safety, discuss the complexities of foreseeing the societal impacts of “AI Afterlives,” and identify key avenues for future research.”
Metadata
- Authors
- Colavizza, G., Blanke, T., Jeurgens, C., & Noordegraaf, J.
- Affiliations
- University of Amsterdam (NL)
- Venue
- Journal on Computing and Cultural Heritage
- Published
- 2021-12-14
- Volume
- 15
- Issue
- 1
- Pages
- 1-15
- ISSN
- 1556-4711 (ISSN-L)
- 1556-4673
- OpenAlex
- W3157353160
- Cited by
- 162
- References
- 64
- Citations by year
- 2026: 38 · 2025: 51 · 2024: 40 · 2023: 23 · 2022: 9 · 2021: 1
- FWCI
- 116.37
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Journal on Computing and Cultural Heritage (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- UvA-DARE (University of Amsterdam) (submittedVersion, cc-by)
- Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna) (submittedVersion, cc-by)
- Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
- arXiv (Cornell University) (cc-by)
- Topics
- Social Sciences › Arts and Humanities › Conservation › Digital and Traditional Archives Management
- Social Sciences › Arts and Humanities › Literature and Literary Theory › Digital Humanities and Scholarship
- Social Sciences › Sociology and Political Science › Data Analysis and Archiving
- Keywords
- artificial intelligence in archives, archival science, records continuum model, digital archives, archival data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-02, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-02 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.