The new designs honor the Constitution, Civil War, and more. Breakthroughs, discoveries, and DIY tips sent every weekday. While we've said goodbye to both the year 2025 and the penny, five new United States quarters will be finding their way into your pocket soon enough. The designs of each new quarter will honor the country's 250th anniversary (aka its semiquincentennial). According to a press release from the U.S. Mint, the coins "commemorate 250 years of American Liberty by reflecting our country's founding principles and honoring our Nation's history."

Science Archaeology Ancient Rome's fanciest glasses are full of cryptic symbols They were the ancient equivalent of a brand.' Breakthroughs, discoveries, and DIY tips sent every weekday. Tiny symbols engraved into ancient Roman drinkware may be more than merely decorative accents. After two years of research, an art historian believes that the designs on glass Roman cage cups are testaments to the skill and collaborative efforts required to craft some of the empire's most renowned pieces of glasswork. The talent of ancient Rome's artisans is displayed across the empire's vast archaeological remains, such as its architecture, mosaics, and sculptures .

Bronze inscriptions from early China are fragmentary and difficult to date. We introduce BIRD(Bronze Inscription Restoration and Dating), a fully encoded dataset grounded in standard scholarly transcriptions and chronological labels. We further propose an allograph-aware masked language modeling framework that integrates domain- and task-adaptive pretraining with a Glyph Net (GN), which links graphemes and allographs. Experiments show that GN improves restoration, while glyph-biased sampling yields gains in dating.

Object-centric process mining investigates the intertwined behavior of multiple objects in business processes. From object-centric event logs, object-centric Petri nets (OCPN) can be discovered to replay the behavior of processes accessing different object types. Although they indicate how objects flow through the process and co-occur in events, OCPNs remain underspecified about the relationships of objects. Hence, they are not able to represent synchronization, i.e. executing objects only according to their intended relationships, and fail to identify violating executions. Existing formal modeling approaches, such as object-centric Petri nets with identifiers (OPID), represent object identities and relationships to synchronize them correctly. However, OPID discovery has not yet been studied. This paper uses explicit data models to bridge the gap between OCPNs and formal OPIDs. We identify the implicit assumptions of stable many-to-one relationships in object-centric event logs, which implies synchronization of related objects. To formally underpin this observation, we combine OCPNs with explicit stable many-to-one relationships in a rigorous mapping from OCPNs to OPIDs explicitly capturing the intended stable relationships and the synchronization of related objects. We prove that the original OCPNs and the resulting OPIDs coincide for those executions that satisfy the intended relationships. Moreover, we provide an implementation of the mapping from OCPN to OPID under stable relationships.

Constructing historical language models (LMs) plays a crucial role in aiding archaeological provenance studies and understanding ancient cultures. However, existing resources present major challenges for training effective LMs on historical texts. First, the scarcity of historical language samples renders unsupervised learning approaches based on large text corpora highly inefficient, hindering effective pre-training. Moreover, due to the considerable temporal gap and complex evolution of ancient scripts, the absence of comprehensive character encoding schemes limits the digitization and computational processing of ancient texts, particularly in early Chinese writing. To address these challenges, we introduce InteChar, a unified and extensible character list that integrates unencoded oracle bone characters with traditional and modern Chinese. InteChar enables consistent digitization and representation of historical texts, providing a foundation for robust modeling of ancient scripts. To evaluate the effectiveness of InteChar, we construct the Oracle Corpus Set (OracleCS), an ancient Chinese corpus that combines expert-annotated samples with LLM-assisted data augmentation, centered on Chinese oracle bone inscriptions. Extensive experiments show that models trained with InteChar on OracleCS achieve substantial improvements across various historical language understanding tasks, confirming the effectiveness of our approach and establishing a solid foundation for future research in ancient Chinese NLP.

Tombstones are historically and culturally rich artifacts, encapsulating individual lives, community memory, historical narratives and artistic expression. Yet, many tombstones today face significant preservation challenges, including physical erosion, vandalism, environmental degradation, and political shifts. In this paper, we introduce a novel multi-modal framework for tombstones digitization, aiming to improve the interpretation, organization and retrieval of tombstone content. Our approach leverages vision-language models (VLMs) to translate tombstone images into structured Tombstone Meaning Representations (TMRs), capturing both image and text information. To further enrich semantic parsing, we incorporate retrieval-augmented generation (RAG) for integrate externally dependent elements such as toponyms, occupation codes, and ontological concepts. Compared to traditional OCR-based pipelines, our method improves parsing accuracy from an F1 score of 36.1 to 89.5. We additionally evaluate the model's robustness across diverse linguistic and cultural inscriptions, and simulate physical degradation through image fusion to assess performance under noisy or damaged conditions. Our work represents the first attempt to formalize tombstone understanding using large vision-language models, presenting implications for heritage preservation.

A fragment of a bronze military diploma from Sardinia, issued by the emperor Trajan to a sailor on a warship, as restored by Aeneas. If you believe the hype, generative artificial intelligence (AI) is the future. However, new research suggests the technology may also improve our understanding of the past. A team of computer scientists from Google DeepMind, working with classicists and archaeologists from universities in the United Kingdom and Greece, described a new machine-learning system designed to help experts to understand ancient Latin inscriptions. Named Aeneas (after the mythical hero of Rome's foundation epic), the system is a generative neural network designed to provide context for Latin inscriptions written between the 7th century BCE and the 8th century CE.

Latin inscriptions from the ancient world can tell us about Roman emperors' decrees and enslaved people's thoughts – if we can read them. Now an artificial intelligence tool is helping historians reconstruct the often fragmentary texts. It can even accurately predict when and where in the Roman Empire a given inscription came from. "Studying history through inscriptions is like solving a gigantic jigsaw puzzle, only this is tens of thousands of pieces more than normal," said Thea Sommerschield at the University of Nottingham in the UK, during a press event. "And 90 per cent of them are missing because that's all that survived for us over the centuries."

It's not the first time AI has been used to join up the missing dots in Roman history. Dr Sommerschield developed Aeneas along with her co-research leader Dr Yannis Assael, an AI specialist at Google DeepMind. It automates the process of contextualising based on parallels, in the blink of an eye. Aeneas draws on a vast database of of 176,000 Roman inscriptions including images and uses a carefully designed AI system to pull up a range of relevant historical parallels, to support the work of historians, according to Dr Assael. "What the historian can't do is assess these parallels in a matter of seconds across tens of thousands of inscriptions, and that is where AI can come in as an assistant."

To do this, Aeneas takes in partial transcriptions of an inscription alongside a scanned image of it. Using these, it gives possible dates and places of origins for the engraving, along with potential fill-ins for any missing text. For example, a slab damaged at the start and continuing with ... us populusque Romanus would likely prompt Aeneas to guess that Senat comes before us to create the phrase Senatus populusque Romanus, "The Senate and the people of Rome." This is similar to how Ithaca works. But Aeneas also cross-references the text with a stored database of almost 150,000 inscriptions, which originated everywhere from modern-day Britain to modern-day Iraq, to give possible parallels--other catalogued Latin engravings that feature similar words, phrases, and analogies.