The paper outlines the ClaReNet project's exploration of computer-based methods for classifying Celtic coin series, specifically focusing on a hoard from Jersey [1]. They collaborated with Jersey Heritage and numismatists, utilising a large dataset of coin images. The process involves stages such as pre-sorting, size-based sorting, class/type identification, and die studies. They employed IT methods, including object detection and unsupervised learning, followed by supervised learning for data refinement. Collaboration with numismatic experts ensured data quality. The study highlighted challenges in classifying coins, suggesting techniques like image matching alongside convolutional neural networks (CNNs). The results demonstrate the efficacy of semi-automatic processes in coin classification, emphasising the importance of human-computer collaboration for successful outcomes.

Overall, this is a good paper, showing how we as archaeologists and numismatics can use existing tools and finetune them for our purposes; without the need for huge domain specific datasets. This research and related papers show how we can more effectively deal with the increasingly bigger data we deal with, saving time on the monotonous and labour intensive tasks, leaving us more time to deal with the big picture. An important strength of the work is the provided public software repository and the dataset. The paper is well written, and a number of images illustrate the methodology as well as the objects used.

Reference

[1] Deligio, C., Tolle, K., and Wigg-Wolf, D. (2024). Supporting the analysis of a large coin hoard with AI-based methods. Zenodo, 8301464, ver. 4 peer-reviewed and recommended by Peer Community in Archaeology. https://doi.org/10.5281/zenodo.8301464

This paper [1] presents an innovative approach to address the prevalent challenge of unbalanced datasets in coin type recognition, shifting the focus from coin class type recognition to coin mint recognition. Despite this shift, the issue of unbalanced data persists. To mitigate this, the authors introduce a method to split larger classes into smaller ones, integrating them into an 'additional class layer'.

Three distinct machine learning (ML) methodologies were employed to identify new possible classes, with one approach utilising unsupervised clustering alongside manual intervention, while the others leverage object detection, and Natural Language Processing (NLP) techniques. However, despite these efforts, overfitting remained a persistent issue, prompting the authors to explore alternative methods such as dataset improvement and Generative Adversarial Networks (GANs).

The paper contributes significantly to the intersection of ML techniques and archaeology, particularly in addressing overfitting challenges. Furthermore, the authors' candid acknowledgment of the limitations of their approaches serves as a valuable resource for researchers encountering similar obstacles.

This study stems from the D4N4 project, aimed at developing a machine learning-based coin recognition model for the extensive "Corpus Nummorum" dataset, comprising over 19,600 coin types and 49,000 coins from various ancient landscapes. Despite encountering challenges with overfitting due to the dataset's imbalance, the authors' exploration of multiple methodologies and transparent documentation of their limitations enriches the academic discourse and provides a foundation for future research in this field.

Reference

[1] Gampe, S. and Tolle, K. (2024). Creating an Additional Class Layer with Machine Learning to counter Overfitting in an Unbalanced Ancient Coin Dataset. Zenodo, 8298077, ver. 4 peer-reviewed and recommended by Peer Community in Archaeology. https://doi.org/10.5281/zenodo.8298077

The paper under review/recommendation deals with Corpus Nummorum (Peter et al. 2024). The Corpus Nummorum (CN) is web portal for ancient Greek coins from various collections (https://www.corpus-nummorum.eu/). The CN is a database and research tool for Greek coins dating between 600 BCE to 300 CE. While many traditional collection databases aim at collecting coins, CN also includes coin dies, coin types and issues. It aims at achieving a complete online coin type catalogue. The paper is not a paper in a traditional sense, but presents the CN as a tool and shows the functionalities in the system. The relevance and the possibilities of the CN for numismatists is made clear in the paper and the merits are clear even for me as a Roman archaeologist and non-numismatist.

The CN was presented as a poster at the CAA 2023 in Amsterdam during “S03. Our Little Minions pt. V: small tools with major impact”, organized by Moritz Mennenga, Florian Thiery, Brigit Danthine and myself (Mennenga et al. 2023). Little Minions help us significantly in our daily work as small self-made scripts, home-grown small applications and small hardware devices. They often reduce our workload or optimize our workflows, but are generally under-represented during conferences and not often presented to the outside world. Therefore, the Little Minions form a platform that enables researchers and software engineers to share these tools (Thiery, Visser and Mennenga 2021). Little Minions have become a well known happening within the CAA-community since we started this in 2018, also because we do not only allow 10-minute lightning talks, but also spontaneous stand-up presentations during the conference. A full list of all minions presented in the past, can be found online: https://caa-minions.github.io/minions/. In a strict sense the CN would not count as a Little Minion, because it is a large project consisting of many minions that help a numismatist in his/her daily work. The CN seems a very Big Minion in that sense.

Personally, I am very happy to see the database being developed as a fully open system and that code can be found on Github (https://github.com/telota/corpus-nummorum-editor), and also made citable with citation information in GitHub (see https://citation-file-format.github.io/) and a version deposited in Zenodo with DOI (Köster and Franke 2024). In addition, the authors claim that the CN will be shared based on the FAIR-principles (Wilkinson et al. 2016, 2019). These guidelines are developed to improve the Findability, Accessibility, Interoperability, and Reuse of digital data. I feel that CN will be a way forward in open numismatics and open archaeology.

The CN is well known within the numismatist community and it was hard to find reviewers in this close community, because many potential reviewers work together with one or more of the authors, or are involved in the project. This also proves the relevance of the CN to the research community and beyond. Luckily, a Roman numismatist and a specialist in digital/computational archaeology were able to provide valuable feedback on the current paper. The reviewers only submitted feedback on the first version of the paper (Peter et al. 2023).

The numismatist was positive on the content and the usefulness of CN for the discipline in general. However, she pointed out some important points that need to be addressed. The digital specialist was positive is various aspects, but also raised some important issues in relation to technical aspects and the explanation thereof. While both were positive on the project and the paper in general, both reviewers pointed out some issues that were largely addressed in the second version of this paper. The revised version was edited throughout and the paper was strongly improved.

The Corpus Nummorum is well presented in this easy to read paper, although the explanations can sometimes be slightly technical. This paper gives a good introduction to the CN and I recommend this for publication. I sincerely hope that the CN will contribute and keep on contributing to the domains of numismatics, (digital) archaeology and open science in general.

References

Köster, J and Franke, C. 2024 Corpus Nummorum Editor. https://doi.org/10.5281/zenodo.10458195

Mennenga, M, Visser, RM, Thiery, F and Danthine, B. 2023 S03. Our Little Minions pt. V: small tools with major impact. In:. Book of Abstracts. CAA 2023: 50 Years of Synergy. Amsterdam: Zenodo. pp. 249–251. https://doi.org/10.5281/ZENODO.7930991

Peter, U, Franke, C, Köster, J, Tolle, K, Gampe, S and Stolba, VF. 2023 CORPUS NUMMORUM – A Digital Research Infrastructure for Ancient Coins. https://doi.org/10.5281/ZENODO.8263518

Peter, U., Franke, C., Köster, J., Tolle, K., Gampe, S. and Stolba, V. F. (2024). CORPUS NUMMORUM – A Digital Research Infrastructure for Ancient Coins, Zenodo, 8263517, ver. 3 peer-reviewed and recommended by Peer Community in Archaeology. https://doi.org/10.5281/zenodo.8263517

Thiery, F, Visser, RM and Mennenga, M. 2021 Little Minions in Archaeology An open space for RSE software and small scripts in digital archaeology. https://doi.org/10.5281/ZENODO.4575167

Wilkinson, MD, Dumontier, M, Aalbersberg, IjJ, Appleton, G, Axton, M, Baak, A, Blomberg, N, Boiten, J-W, da Silva Santos, LB, Bourne, PE, Bouwman, J, Brookes, AJ, Clark, T, Crosas, M, Dillo, I, Dumon, O, Edmunds, S, Evelo, CT, Finkers, R, Gonzalez-Beltran, A, Gray, AJG, Groth, P, Goble, C, Grethe, JS, Heringa, J, ’t Hoen, PAC, Hooft, R, Kuhn, T, Kok, R, Kok, J, Lusher, SJ, Martone, ME, Mons, A, Packer, AL, Persson, B, Rocca-Serra, P, Roos, M, van Schaik, R, Sansone, S-A, Schultes, E, Sengstag, T, Slater, T, Strawn, G, Swertz, MA, Thompson, M, van der Lei, J, van Mulligen, E, Velterop, J, Waagmeester, A, Wittenburg, P, Wolstencroft, K, Zhao, J and Mons, B. 2016 The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data 3(1): 160018. https://doi.org/10.1038/sdata.2016.18

Wilkinson, MD, Dumontier, M, Jan Aalbersberg, I, Appleton, G, Axton, M, Baak, A, Blomberg, N, Boiten, J-W, da Silva Santos, LB, Bourne, PE, Bouwman, J, Brookes, AJ, Clark, T, Crosas, M, Dillo, I, Dumon, O, Edmunds, S, Evelo, CT, Finkers, R, Gonzalez-Beltran, A, Gray, AJG, Groth, P, Goble, C, Grethe, JS, Heringa, J, Hoen, PAC ’t, Hooft, R, Kuhn, T, Kok, R, Kok, J, Lusher, SJ, Martone, ME, Mons, A, Packer, AL, Persson, B, Rocca-Serra, P, Roos, M, van Schaik, R, Sansone, S-A, Schultes, E, Sengstag, T, Slater, T, Strawn, G, Swertz, MA, Thompson, M, van der Lei, J, van Mulligen, E, Jan Velterop, Waagmeester, A, Wittenburg, P, Wolstencroft, K, Zhao, J and Mons, B. 2019 Addendum: The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data 6(1): 6. https://doi.org/10.1038/s41597-019-0009-6

The advent of biomolecular methods has certainly increased our overall comprehension of archaeological societies. One of the materials of choice to perform ancient DNA or proteomics analyses is dental calculus[1,2], a mineralised biofilm formed during the life of one individual. Research conducted in the past few decades has demonstrated the potential of dental calculus to retrieve information about past societies health[3–6], diet[7–11], and more recently, as a putative proxy for isotopic analyses[12]. 

Based on a proof-of-concept previously published by their team[13], Bartholdy and collaborators’ paper presents the identification of compounds and their secondary metabolites derived from consumed plants in individuals from a XIXth century rural Dutch archaeological deposit[14]. Sørensen indeed demonstrated that drug intake is recorded in dental calculus, which are mineralised biofilms that can encapsulate drug compounds long after the latter are no longer detectable in blood. The liquid-chromatography coupled to mass spectrometry (LC-MS/MS)-based method developed showed the potential for archaeological applications[13]. 

Bartholdy et al. utilised the developed LC-MS/MS method to 41 buried individuals, most of them bearing pipe notches on their teeth, from the cemetery of the 19th rural settlement of Middenbeemster, the Netherlands. Along with dental calculus sampling and analysis, they undertook the skeletal and dental examination of all of the specimens in order to assess sex, age-at-death, and pathology on the two tissues. The results obtained on the dental calculus of the sampled individuals show probable consumption of tea, coffee and tobacco indicated by the detection of the various plant compounds and associated metabolites (caffeine, nicotine and salicylic acid, amongst others). 

The authors were able to place their results in perspective and propose several interpretations concerning the ingestion of plant-derived products, their survival in dental calculus and the importance of their findings for our overall comprehension of health and habits of the XIXth c. Dutch population. The paper is well-written and accessible to a non-specialist audience, maximising the impact of their study. I personally really enjoyed handling this manuscript that is not only a good piece of scientific literature but also a pleasant read, the reason why I warmly recommend this paper to be accessible through PCI Archaeology.

References

1.      Fagernäs, Z. and Warinner, C. (2023) Dental Calculus. in Handbook of Archaeological Sciences 575–590. https://doi.org/10.1002/9781119592112.ch28

2.      Wright, S. L., Dobney, K. & Weyrich, L. S. (2021) Advancing and refining archaeological dental calculus research using multiomic frameworks. STAR: Science & Technology of Archaeological Research 7, 13–30. https://doi.org/10.1080/20548923.2021.1882122

3.      Fotakis, A. K. et al. (2020) Multi-omic detection of Mycobacterium leprae in archaeological human dental calculus. Philos. Trans. R. Soc. Lond. B Biol. Sci. 375, 20190584. https://doi.org/10.1098/rstb.2019.0584

4.      Warinner, C. et al. (2014) Pathogens and host immunity in the ancient human oral cavity. Nat. Genet. 46, 336–344. https://doi.org/10.1038/ng.2906

5.      Weyrich, L. S. et al. (2017) Neanderthal behaviour, diet, and disease inferred from ancient DNA in dental calculus. Nature 544, 357–361. https://doi.org/10.1038/nature21674

6.      Jersie-Christensen, R. R. et al. (2018) Quantitative metaproteomics of medieval dental calculus reveals individual oral health status. Nat. Commun. 9, 4744. https://doi.org/10.1038/s41467-018-07148-3

7.      Hendy, J. et al. (2018) Proteomic evidence of dietary sources in ancient dental calculus. Proc. Biol. Sci. 285. https://doi.org/10.1098/rspb.2018.0977

8.      Wilkin, S. et al. (2020) Dairy pastoralism sustained eastern Eurasian steppe populations for 5,000 years. Nat Ecol Evol 4, 346–355. https://doi.org/10.1038/s41559-020-1120-y

9.      Bleasdale, M. et al. (2021) Ancient proteins provide evidence of dairy consumption in eastern Africa. Nat. Commun. 12, 632. https://doi.org/10.1038/s41467-020-20682-3

10.   Warinner, C. et al. (2014) Direct evidence of milk consumption from ancient human dental calculus. Sci. Rep. 4, 7104. https://doi.org/10.1038/srep07104

11.   Buckley, S., Usai, D., Jakob, T., Radini, A. and Hardy, K. (2014) Dental Calculus Reveals Unique Insights into Food Items, Cooking and Plant Processing in Prehistoric Central Sudan. PLoS One 9, e100808. https://doi.org/10.1371/journal.pone.0100808

12.   Salazar-García, D. C., Warinner, C., Eerkens, J. W. and Henry, A. G. (2023) The Potential of Dental Calculus as a Novel Source of Biological Isotopic Data. in Exploring Human Behavior Through Isotope Analysis: Applications in Archaeological Research (eds. Beasley, M. M. & Somerville, A. D.) 125–152. https://doi.org/10.1007/978-3-031-32268-6_6

13.   Sørensen, L. K., Hasselstrøm, J. B., Larsen, L. S. and Bindslev, D. A. (2021) Entrapment of drugs in dental calculus - Detection validation based on test results from post-mortem investigations. Forensic Sci. Int. 319, 110647. https://doi.org/10.1016/j.forsciint.2020.110647

14.   Bartholdy, Bjørn Peare, Hasselstrøm, Jørgen B., Sørensen, Lambert K., Casna, Maia, Hoogland, Menno, Historisch Genootschap Beemster and Henry, Amanda G. (2023) Multiproxy analysis exploring patterns of diet and disease in dental calculus and skeletal remains from a 19th century Dutch population, Zenodo, 7649150, ver. 5 peer-reviewed and recommended by Peer Community in Archaeology. https://doi.org/10.5281/zenodo.7649150

The paper “HORAI: An integrated management model for historical information” presents a novel model for managing historical information. The study draws from an extensive indepth work in historical information management and a multi-disciplinary corpus of research ranging from heritage infrastructure research and practice to information studies and archival management literature. The paper ties into several key debates and discussions in the field showing awareness of the state-of-the-art of data management practice and theory. The authors argue for a new semantic data model HORAI and link it to a four-phase data management lifecycle model. The conceptual work is discussed in relation to three existing information systems partly predating and partly developed from the outset of the HORAI-model.

While the paper shows appreciable understanding of the practical and theoretical state-of-the-art and the model has a lot of potential, in its current form it is still somewhat rough on the edges. Many of the both practical and theoretical threads introduced in the text warrant also more indepth consideration and it will be interesting to follow how the work will proceed in the future. For example, the comparison of the HORAI model and the ISAD(G): General International Standard Archival Description standard in the figure 1 is interesting but would require more elaboration. A slightly more thorough copyediting of the text would have also been helpful to make it more approachable.

As a whole, in spite of the critique, I find both the paper and the model as valuable contributions to the literature and the practice of managing historical information. The paper reports thorough work, provides a lot of food for thought and several interesting lines of inquiry in the future.

References

Del Fresno Bernal, P., Medina Gordo, S. and Travé Allepuz, E. (2024). HORAI: An integrated management model for historical information. CAA 2023, Amsterdam, Netherlands. https://doi.org/10.5281/zenodo.8185510