Abstract The new digital technologies have become an effective tool for researchers in different fields. Historians and archaeologists who are studying Greek and Roman Libya have benefited from technical developments in presenting different kinds of data, particularly relating to the epigraphy and toponymy of Libya. They have recently published several resources, and are working on more. This study presents the story of how scholars have collected a variety of Libyan heritage materials and published them online; the account makes it clear that these digital projects are the result of extensive and ongoing collaboration between researchers from different countries, including Libya. They have worked together, and are still working to produce valuable online corpora of inscriptions alongside the Heritage Gazetteer of Libya which records names used at different times, and in a variety of languages, of heritage sites. We also discuss plans for further improving the accessibility of these materials, and encouraging their wider use. , أصبحت التقنيات الرقمية الحديثة أداة فعالة للباحثين في مجالات مختلفة، وقد استفاد المؤرخون والآثاريون، المهتمون بتاريخ ليبيا وآثارها في الفترتين الإغريقية والرومانية، من التطورات التقنية لتقديم بيانات (data) مختلفة وخاصة تلك المتعلقة بالنقوش ودراسة مسميات المواقع الأثرية بليبيا. قام هؤلاء حديثاً بنشر مصادر متعددة، معضمها لنقوش، ولا يزال العمل مستمر على أعمال أخرى. توضح هذه الدراسة الكيفية التي تمكن خلالها الباحثون من جمع مواد متنوعة من التراث الليبي، ثم نشرها لتكون متاحة للجميع على الشبكة العنكبوتية (الإنترنت). تُبين هذه الورقة بشكل جلي أن هذه المشاريع الرقمية جاءت نتيجة تعاون مكثف ودؤوب بين باحثين من بلدان عِدَّة بما فيها ليبيا. حيث عملوا معاً ولا يزالوا مستمرين في تقديم مجموعة قيمة للنقوش الإغريقية واللاتينية، بالإضافة إلى فهرس جغرافي يسجل اسماء لمواقع أثرية اُستخدمت في حقب مختلفة وسُميت بلغات متعددة. كما ناقشت هذه الورقة خططاً من شأنها تطويرإمكانية الوصول لهذه المواد التراثية وتشجيع استخدامها على نطاق موسع .

Questo contributo illustra un’efficace esperienza di collaborazione tra diverse istituzioni, quali enti di ricerca, di tutela e formazione, e differenti professionalitá, coinvolte nell’ambito dell’alternanza scuola-lavoro, ai fini della digitalizzazione e valorizzazione del patrimonio epigrafico del Museo Civico Castello Ursino del Comune di Catania. Il Museo possiede una rilevante collezione epigrafica, costituita da due raccolte settecentesche catanesi. Alcune iscrizioni sono esposte secondo i vecchi criteri di fruizione museale; la maggior parte é custodita in deposito. Uno degli obiettivi dell’esperienza é dunque far conoscere al pubblico fruitore ed alla comunitá degli studiosi l’ingente patrimonio epigrafico del Castello attualmente non esposto al pubblico. Il progetto di durata triennale é stato caratterizzato in un primo momento da una attivitá di digitalizzazione di schede catalografiche e di documentazione grafica e fotografica di parte delle epigrafi; durante il secondo anno di attivit. é stata realizzata una esposizione presso il Castello Ursino di un gruppo selezionato di epigrafi di provenienza catanese, che sono state sottoposte a un primo restauro conservativo ed inserite nel catalogo digitale con la relativa documentazione. Le epigrafi sono codificate secondo standard e vocabolari controllati internazionali (formatto EpiDoc TEI XML, Pleiades per posizioni geografiche e lessici controllati di EAGLE per i tipi di iscrizioni, i materiali e i supporti) al fine di consentire la creazione di Linked Open Data. La mostra presenta, tra l’altro, la realizzazione di due video e l’inserimento di un chiosco digitale multimediale per accedere a contenuti di approfondimento e immagini 3D. Durante il terzo anno é programmata la prosecuzione dell’attivit. di digitalizzazione e documentazione ed un approfondimento della disseminazione dei risultati sul web.

Epigraphy is witnessing a growing integration of artificial intelligence, notably through its subfield of machine learning (ML), especially in tasks like extracting insights from ancient inscriptions. However, scarce labeled data for training ML algorithms severely limits current techniques, especially for ancient scripts like Old Aramaic. Our research pioneers an innovative methodology for generating synthetic training data tailored to Old Aramaic letters. Our pipeline synthesizes photo-realistic Aramaic letter datasets, incorporating textural features, lighting, damage, and augmentations to mimic real-world inscription diversity. Despite minimal real examples, we engineer a dataset of 250 000 training and 25 000 validation images covering the 22 letter classes in the Aramaic alphabet. This comprehensive corpus provides a robust volume of data for training a residual neural network (ResNet) to classify highly degraded Aramaic letters. The ResNet model demonstrates 95% accuracy in classifying real images from the 8th century BCE Hadad statue inscription. Additional experiments validate performance on varying materials and styles, proving effective generalization. Our results validate the model’s capabilities in handling diverse real-world scenarios, proving the viability of our synthetic data approach and avoiding the dependence on scarce training data that has constrained epigraphic analysis. Our innovative framework elevates interpretation accuracy on damaged inscriptions, thus enhancing knowledge extraction from these historical resources.

Human history is born in writing. Inscriptions are among the earliest written forms, and offer direct insights into the thought, language and history of ancient civilizations. Historians capture these insights by identifying parallels—inscriptions with shared phrasing, function or cultural setting—to enable the contextualization of texts within broader historical frameworks, and perform key tasks such as restoration and geographical or chronological attribution. However, current digital methods are restricted to literal matches and narrow historical scopes. Here we introduce Aeneas, a generative neural network for contextualizing ancient texts. Aeneas retrieves textual and contextual parallels, leverages visual inputs, handles arbitrary-length text restoration, and advances the state of the art in key tasks. To evaluate its impact, we conduct a large study with historians using outputs from Aeneas as research starting points. The historians find the parallels retrieved by Aeneas to be useful research starting points in 90% of cases, improving their confidence in key tasks by 44%. Restoration and geographical attribution tasks yielded superior results when historians were paired with Aeneas, outperforming both humans and artificial intelligence alone. For dating, Aeneas achieved a 13-year distance from ground-truth ranges. We demonstrate Aeneas’ contribution to historical workflows through analysis of key traits in the renowned Roman inscription Res Gestae Divi Augusti, showing how integrating science and humanities can create transformative tools to assist historians and advance our understanding of the past.

Ancient history relies on disciplines such as epigraphy—the study of inscribed texts known as inscriptions—for evidence of the thought, language, society and history of past civilizations1. However, over the centuries, many inscriptions have been damaged to the point of illegibility, transported far from their original location and their date of writing is steeped in uncertainty. Here we present Ithaca, a deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions. Ithaca is designed to assist and expand the historian’s workflow. The architecture of Ithaca focuses on collaboration, decision support and interpretability. While Ithaca alone achieves 62% accuracy when restoring damaged texts, the use of Ithaca by historians improved their accuracy from 25% to 72%, confirming the synergistic effect of this research tool. Ithaca can attribute inscriptions to their original location with an accuracy of 71% and can date them to less than 30 years of their ground-truth ranges, redating key texts of Classical Athens and contributing to topical debates in ancient history. This research shows how models such as Ithaca can unlock the cooperative potential between artificial intelligence and historians, transformationally impacting the way that we study and write about one of the most important periods in human history.

The Digital Archive for the Study of Pre-Islamic Arabian Inscriptions (DASI) is a five-year ERC project of the University of Pisa, directed by Prof. A. Avanzini. Started in May 2011, the project seeks to collect the whole corpus of pre-Islamic Arabian inscriptions in an open-access archive, with the aim of fostering studies and scientific publications on the epigraphic heritage of Arabia. The paper describes the main activities carried out in the first two years of the project: the IT research on the cataloguing methodologies of the epigraphic material, the digitization of thousands of pre-Islamic Arabian inscriptions, and the setting up of the archive website for the fruition of the catalogued material, which opened in October 2013. The project also encourages the involvement of international partners and promotes interest in pre-Islamic Arabia through a series of related activities and projects, such as the IVIEDINA digital library and the IMTO archaeological database, which are promoted in the Arabia Antica portal of the University of Pisa.

Cuneiform tablets remain founding cornerstones of two hundred plus collections in American academic institutions, having been acquired a century or more ago under dynamic ethical norms and global networks. To foster data sharing, this contribution incorporates empirical data from interactive ArcGIS and reusable OpenContext maps to encourage tandem dialogues about using the inscribed works and learning their collecting histories. Such provenance research aids, on their own, initiate the narration of objects’ journeys over time while cultivating the digital inclusion of expert local knowledge relevant to an object biography. The paper annotates several approaches institutions are or might consider using to expand upon current provenance information in ways that encourage visitors’ critical thinking and learning about global journeys, travel archives, and such dispositions as virtual reunification, reconstructions, or restitution made possible by the provenance research.

Il contributo fornisce una breve storia di EAGLE: nasce nel 2003 come Electronic Archive of Greek and Latin Epigraphy, una federazione di banche dati che si riconoscono nello stesso modo di concepire l’epigrafia digitale; si evolve tra il 2013 e il 2016 come aggregatore e content provider di Europeana (Europeana network of Ancient Greek and Latin Epigraphy); dal 2020 accoglie EDF (Epigraphic Database Falsae), la prima banca dati dedicata al fenomeno della falsificazione epigrafica.

New instruments can lead to radical changes in scientific knowledge: the role of Galileo's telescope in the revolution in astronomy is well known in this respect. I am convinced that the use of computer technology must hold an analogous function in the humanities. So far, this role has been under-valued because of the technical means' former embryonic status. However, the power of today's computers is transforming the ways in which we do research: quantitative change eventually leads to qualitative change. We can now engage in cross queries of vast corpuses in a way unimaginable only ten years ago. In addition, thanks to networking, all of the documentation is potentially accessible from any point on the planet, or at least nearly so. I would like to present an example of computer use that suggests a paradoxical situation. We can now exploit the oldest archives of humanity by using the latest computer technology, making them available to all via an online database. The “Archibab” project began six years ago in response to a call for proposals entitled, “Corpus and tools for research in the humanities” issued by the French National Research Agency. It covers Mesopotamian records from the Old Babylonian period, dating from the 20th –17th B.C.E., hence the acronym ARCHIBAB (Fr., “ARCHIves BAByloniennes;” Eng. “Babylonian archives”) by which the project is designated. I would like first to define the spirit that guided the development of this project; second, to give concrete examples of what we can ask of the Website created through this project; and finally to outline the developing prospects for the coming years.

Le VÉgA, ou Vocabulaire de l’Égyptien Ancien, est un dictionnaire en ligne qui vise à devenir pour l’égyptologie une source incontournable et actualisée, ainsi qu’un support de collaborations scientifiques pour les décennies à venir. Le VÉgA permet de modéliser et représenter les connaissances évolutives en égyptien ancien, en regroupant et recoupant les mots, leurs attestations, leurs références, leurs graphies exactes en hiéroglyphes. Cet outil est le fruit d’une collaboration public/privé dans le cadre du LabEx Archimede de l’Université Paul-Valéry Montpellier 3. Le VÉgA résulte d’une approche nouvelle dans les sciences humaines et sociales, en l’occurrence l’égyptologie, intégrant les méthodes et les outils du design dans la recherche scientifique. Le LabEx Archimede s’est adjoint le savoir-faire d’une agence disposant d’une expérience de recherche par le design qui correspondait parfaitement aux besoins des égyptologues.

This work presents a corpus of transliterated cuneiform tablets from the Electronic Babylonian Library (eBL) platform, including a public API endpoint to download the latest version of the data, and a Python library to parse the transliterations in ATF format. As of the time of writing, the constantly growing dataset contains around 25,000 tablets with over 350,000 lines of transliterated text. This dataset is a sizeable addition to open-source cuneiform data and a major milestone for research within the fields of cuneiform studies and NLP.

Comme Gaignières en son temps, les dynamiques actuelles et les politiques publiques d’ouverture des données réinterrogent les dispositifs de collecte, de mise à disposition et d’exploitation des corpus d’informations qui aujourd’hui sont numériques. Se mettent en place des hubs de données, sortes de collections multiformes qui se développent aussi bien en local sur notre territoire qu’au niveau international. Ces objets qui sont aujourd'hui appelés entrepôts de données ne sont pas neutres et détermineront le paysage de la recherche sur le patrimoine de demain. Cette communication entend s’interroger sur ces objets pour lesquels la dimension technique et les interfaces jouent un rôle majeur. Il s’agit aussi de réfléchir dans quelle mesure, comme pour la collection Gaignières, ces outils influent sur nos dynamiques de connaissance. Nous utiliserons pour illustrer nos propos un nouvel outil, que nous souhaitons mettre en perspective : la plateforme open data La Fabrique Numérique du Passé. La Fabrique Numérique du Passé (FNP), plateforme open data pour les données géohistoriques se fixe comme objectif de développer pour les sciences du patrimoine et du passé des outils accessibles de capitalisation et de mise à disposition des données, respectant les principes de l’open data et du fair data. FNP s’adresse aux acteurs de la recherche afin de leur permettre de s’impliquer simplement dans une démarche d’ouverture des données qui prend pied dans le mouvement plus global de l’open science (ouvrirlascience.fr). Plus fonctionnellement, il s’agit d’agglomérer l’information existante et de mettre à disposition de tous, en libre téléchargement, les données produites dans le cadre de projets et programmes de recherche (PCR, ANR, ERC...) dans leur format standard le plus « accessible » afin d’être facilement réutilisables par l’ensemble des acteurs du monde socio-économique et des acteurs du territoire. La Fabrique numérique du passé, permet ainsi de faire la jonction pour nos disciplines entre des lieux de dépôts pérennes (entrepôts de données comme Nakala pour les Sciences Humaines et Sociales), des acteurs qui produisent des données dans le cadre de projets de recherche et un capital de données qui doit être à la fois pérennisé et accessible pour être mobilisé par de nouveaux acteurs. , Like Gaignières in his day, current trends and public policies to open up data are re-examining the mechanisms for collecting, making available and exploiting bodies of information that are now digital. Data hubs are being set up, multiform collections developing both locally in France and internationally. These objects, now known as data warehouses, are not neutral and will determine the landscape of heritage research in the future. The aim of this paper is to examine these objects, whose technical dimension and interfaces play a major role. It will also look at the extent to which, as in the case of the Gaignières collection, these tools influence the dynamics of our knowledge. To illustrate this, we will be using a new tool that we hope to put into perspective: the open data platform La Fabrique Numérique du Passé. La Fabrique Numérique du Passé (FNP), an open data platform for geohistorical data, has set itself the goal of developing accessible tools for the sciences of heritage and the past to capitalise on and make available data, in accordance with the principles of open data and fair data. FNP is aimed at research players, enabling them to get involved in a simple process of opening up data as part of the wider open science movement (ouvrirlascience.fr). More functionally, the aim is to bring together existing information and make the data produced as part of research projects and programmes (PCR, ANR, ERC, etc.) available for free download in the most “accessible” standard format so that it can be easily reused by all socioeconomic players and local stakeholders. The FNP is a way of bridging the gap for our disciplines between permanent repositories (data warehouses such as Nakala for the humanities and social sciences), players who produce data as part of research projects and a pool of data that needs to be both durable and accessible so that it can be mobilised by new players.