The authors, Rogelio Pérez Moreira and María Teresa Barral Silva, frame their argument around a simple observation: soil is usually shown only at its surface, and rarely in profile, the three-dimensional cross-section that soil scientists study. A soil profile only becomes visible in a painting when the ground is cut open, along a road cutting, a slope or an escarpment. Yet even then, the internal differentiation of horizons would rarely be observable without deliberate excavation, something inconceivable in eras long before scientific soil study. The striking exception, they find, is that certain paintings show textures, colors and chromatic sequences that correspond to real soil features identifiable today, including dark surface horizons and even the bleached eluvial and reddish illuvial layers of podzols.

The precursors are revealing. Medieval and Renaissance artists showed soil mainly as surface, as in the plowed fields of the Très Riches Heures du Duc de Berry from 1413 to 1416 or Pieter Brueghel the Elder’s The Fall of Icarus from around 1558 to 1560. Where the ground was opened, as in works by Rogier van der Weyden, Hans Memling, Hieronymus Bosch or Giorgione, the exposed earth often carried symbolic weight, serving as an allegory of resurrection or an excuse to display roots with their own emblematic meaning. Occasionally a real profile emerges, as in Giovanni Agostino da Lodi’s Pan and Syrinx of around 1510, where a darkened A horizon shows above a talus, or in the deep reddish-brown cuttings of 17th-century Flemish painter Lodewijk de Vadder. But these remain exceptions against a convention in which soil was scenery, not subject.

The first true flowering came with the birth of landscape painting itself. Art historians generally agree that landscape became an autonomous genre at the start of the 17th century in the Nordic countries, and definitively in Holland. The context was revolutionary: the Seven United Provinces had declared independence from Spain in 1579, Protestantism replaced Catholicism, and a powerful commercial bourgeoisie transformed the art market. With courtly and ecclesiastical patronage gone, and the Reformed Church proscribing religious imagery, the new merchant class collected small-format paintings of the world around them. By mid-century, landscapes made up nearly 40 percent of Dutch artistic production, bought by all classes of society, driven by civic pride in a free country, nostalgia for a rural past among an increasingly urban population, and a special relationship with land reclaimed from wetlands around Haarlem and Amsterdam.

Dutch painters rarely finished canvases outdoors, but they went into the field to sketch from nature, and those excursions let them perceive details and subtleties that studio-bound traditions had never registered. The result was a naturalism built on thorough observation of specifics, even if the final works were believable reconstructions rather than literal transcriptions. Crucially for soil scientists, much of the Netherlands sits on drifting sand deposits, whose buried paleosols commonly show podzolic characteristics, with a pale leached E horizon above a dark spodic B horizon. A whole school of painters specialized in dune landscapes: Esaias van de Velde, Jan van Goyen, Pieter de Molijn and Salomon van Ruysdael established a tonal phase of warm grays and earth tones, later monumentalized by Jacob van Ruisdael, Meindert Hobbema and Philips Wouwerman.

The profiles in these paintings grow steadily more eloquent. Aelbert Cuyp’s river scenes and wooded landscapes show the dark surface horizon clearly. Salomon van Ruysdael’s Landscape with Sandy Road of 1628 presents an upper horizon thick with roots. But the standout is Jan Wijnants of Haarlem, who devoted his entire career to dune paintings. After moving permanently to Amsterdam in December 1660, his canvases began showing soil details that the authors describe as exceptional for their time and undoubtedly the result of prior observation. In works such as The Dunes near Haarlem of 1667, the dark A horizon sits above the dune substrate, and in several paintings the pale eluvial E horizon and the underlying illuvial spodic B horizon of a podzol can be distinguished, a sequence any soil scientist would recognize today.

The second flowering came two centuries later, in the 19th century, when industrial prosperity empowered a new bourgeoisie and artists, freed from painting the grandeur of monarchs, developed their individuality and absorbed the excitement of the natural sciences. The Dutch masters themselves became the models: Thomas Gainsborough and John Constable studied Ruisdael, Hobbema and Wijnants with devoted admiration, and the Dutch contribution to European landscape was ultimately its naturalism. Plein air painting, rare and technically difficult before the invention of paint tubes and portable easels at mid-century, became a genuine practice. Romanticism had elevated landscape to academic respectability; Realism then demanded that nature be reproduced truthfully, as John Ruskin urged in Modern Painters, without rejecting, choosing or despising anything. Natural elements were no longer decorative props but singular entities reproduced according to their own reality.

Three schools carried this new naturalism, and all three left soil records. In England, Constable, painting outdoors from 1810 onward, showed the soil profile clearly in works such as Dedham Vale of 1802 and Dell at Helmingham Park from the mid-1820s, where the surface horizon and other features are distinguishable. In France, the creation of the Grand Prix de Rome for historical landscape in 1817 sent candidates into the Forest of Fontainebleau for the dreaded tree test, seeding the Barbizon School. Early figures Georges Michel and Làzare Bruandet showed profiles in Fontainebleau scenes, and Jacques-Raymond Brascassat, who studied in Italy after winning second prize in 1825, made the soil profile evident in Rochers en forêt of 1828, while Jean-Baptiste-Camille Corot’s Carrière de Chaise-Marie à Fontainebleau of 1831 offers a deliberately unpicturesque fragment of nature that appears drawn directly from life, soil included. In the Netherlands, the Hague School’s Willem Roelofs, who visited Fontainebleau three times, rendered soil with meticulous realism, whether as the surface of an old riverbed or in his detailed Forest of Fontainebleau.

The authors’ conclusion is that the most faithful pictorial representations of soil in Western art coincide precisely with the two periods when naturalistic landscape painting flourished, the 17th and 19th centuries, because exceptional social and cultural circumstances favored open-air observation. When those circumstances vanished, so did the soil. The 18th century’s academic criteria and the late 19th century’s turn toward Impressionism, Symbolism and eventually abstraction replaced faithful description with conceptual and subjective codes, and the recognizable soil profile disappeared from painting. Under modern aesthetics, external reality gave way to visions born from the artist’s spirit, and soil returned to being scenery, or in contemporary Land Art and Eco Art, a physical medium rather than an image.

Why does this matter beyond art history? The researchers argue that paintings can serve as a documentary source and cultural indicator, testifying to how soil was perceived in periods long before pedology, a science only about 150 years old with the Russian scientist Vasily Dokuchaev as its founding reference. Artistic images of soil, they suggest, can also help soil scientists communicate with a broader public, attracting attention beyond the restricted audience of specialists and opening an interdisciplinary dialogue between science and the humanities. In an era when soil degradation and security are urgent global concerns, the idea that a 17th-century dune painting can double as a pedological document, and that Dutch Golden Age canvases once helped a young republic celebrate its land, gives one of humanity’s most overlooked resources an unexpectedly vivid cultural afterlife.

Subject of Research: The representation of soil and soil profiles in naturalistic landscape painting of the 17th and 19th centuries

Article Title: Soil in Art. Its Representation in Naturalistic Painting of the 17th and 19th Centuries

Article References: Pérez Moreira, R., & Barral Silva, M. T. (2025). Soil in Art. Its Representation in Naturalistic Painting of the 17th and 19th Centuries. Spanish Journal of Soil Science, 15, Article 14834. https://doi.org/10.3389/sjss.2025.14834

Image Credits: AI Generated

DOI: 10.3389/sjss.2025.14834

Keywords: soil science, pedology, art history, landscape painting, Dutch Golden Age, Barbizon School, Hague School, John Constable, Jan Wijnants, soil horizons, podzol, plein air painting

The thorny oyster is one of the most distinctive bivalves in the Mediterranean Sea. Its heavy, fluted shell is armored with prominent spines, and the animal cements itself directly to rocky substrates, hinge-down, with the vividly colored interior of the valves facing outward. When the shell gapes, that interior flashes a striking palette that has long caught the human eye. The species is endemic to the Mediterranean, meaning it occurs naturally nowhere else, and it shares its range today with a relative, the invasive Spondylus spinosus, which has spread through the eastern basin after entering via the Suez Canal. Mapping the two species’ current distributions, using occurrence data from GBIF, was one of the technical threads of the new analysis, providing a modern baseline against which the historical record could be compared.

The central methodological move of the study is interdisciplinary triangulation. The researchers combed fine art collections for depictions of the animal, searched archival and literary sources for references to its collection and consumption, and gathered testimonies documenting more recent uses. Paintings proved to be an unexpectedly rich archive: because artists rendered the thorny oyster’s unmistakable spiny valves in still lifes and kitchen scenes, those canvases function as dated visual records of where and how the species appeared in human settings. When a seventeenth- or eighteenth-century Italian painter placed a Spondylus shell on a fishmonger’s stall or a banquet table, the image preserved evidence of a trade and a taste that written sources often passed over in silence.

What emerges from that triangulated evidence is a portrait of a mollusk with genuine cultural and culinary standing. Historical texts and testimonies indicate that the thorny oyster was eaten in Mediterranean communities, and the visual record places it in contexts of food preparation and display. The animal’s flesh, like that of other edible bivalves, was a local seafood resource, and its dramatic shell gave it a presence on the table and in the market that plainer clams could not match. The study’s title phrase, hidden in historical sources, captures the point: the species’ role in daily life was never entirely erased, but it was dispersed across media that specialists rarely read together, from oil paintings to cookery references to the recollections of people who still encounter the shell on southern Italian coasts.

Italy sits at the heart of the story. The researchers’ analysis of Italian paintings anchors the rediscovery, and modern field records confirm that the living animal remains part of the region’s marine landscape. One of the photographs accompanying the study shows a Spondylus gaederopus specimen photographed by a restaurant customer in Apulia, in southern Italy, in January 2020, a small but telling sign that the species still surfaces in the contemporary culinary world. Another image, taken in September 2025 at a rocky outcrop at Ile Jarre in the western Mediterranean, documents the animal in its natural habitat, cemented among the rocks with its spiny valves intact. Together, the photographs bridge the gap between the historical archive and the living sea.

The distribution maps assembled for the paper add a conservation dimension to the story. Plotting occurrences of the endemic Spondylus gaederopus across the Mediterranean alongside those of the invasive Spondylus spinosus reveals two species with overlapping ranges but very different trajectories. The invasive thorny oyster, which colonized the eastern Mediterranean after migrating through the Suez Canal, has established populations across large areas, while the endemic species’ documented occurrences are more scattered. For a bivalve that has been harvested by humans for centuries, understanding where it persists today is a prerequisite for any effort to manage its populations, and the historical record assembled in the study provides a baseline for judging how much its footprint in human culture has contracted.

The rediscovery also has implications for how scientists think about shifting baselines in marine ecosystems and in human foodways. When a species fades from markets, menus, and paintings, each generation inherits a slightly narrower sense of what the sea once provided. By recovering the thorny oyster’s presence in Italian art and archives, the study shows that the animal’s cultural footprint was once considerably larger than its current low profile suggests. That kind of reconstruction matters for marine historical ecology, a field that uses archives, archaeology, and art to establish what ocean life looked like before modern surveys began. A painting, in this framework, is not merely an aesthetic object but a data point with a date, a location, and a documented subject.

The technical rigor of the study rests on careful identification. Spondylus shells are variable, and distinguishing the endemic gaederopus from the invasive spinosus requires attention to spine arrangement, valve morphology, and coloration, features that skilled painters often captured well enough to permit identification. Linnaeus himself formally described Spondylus gaederopus in 1758, in the tenth edition of his Systema Naturae, the founding document of zoological nomenclature, which gives the species a fixed name that has anchored three centuries of records. The researchers’ combination of Linnaean taxonomy, GBIF occurrence data, QGIS mapping with Natural Earth public-domain base layers, art historical analysis, and testimony collection reflects a deliberately multi-source design intended to make the forgotten history verifiable rather than anecdotal.

Why did such a conspicuous animal become forgotten in the first place? The study does not offer a single cause, but the pattern it documents is consistent with broader changes in Mediterranean fisheries and food culture. Bivalves that require rocky substrates and careful collection are vulnerable to overharvesting and habitat change, and culinary fashions shift as supply chains industrialize. As the thorny oyster receded from markets, the memory of its use receded with it, surviving mainly in old canvases and old texts. The invasive Spondylus spinosus, meanwhile, has been colonizing the eastern basin, in some places becoming abundant enough to attract renewed attention as a potential resource, an irony that underscores how quickly human relationships with marine species can invert.

The broader lesson of the research is methodological as much as biological. The authors, writing in PLOS One with no declared competing interests, argue through their evidence that art, archives, and cultural knowledge constitute a genuine scientific archive for marine species, one that can be mined systematically. Their reconstruction of the thorny oyster’s history shows that a mollusk can be simultaneously a biological organism with a mapped distribution, a culinary resource with a documented past, and a visual motif with a place in the history of Italian painting. Recovering all three strands at once not only restores the species to view but also equips conservationists, historians, and gastronomes with a fuller picture of what has been lost, what survives, and what might yet be rediscovered along the Mediterranean’s rocky shores.

Subject of Research: The cultural and culinary history of the Mediterranean thorny oyster Spondylus gaederopus reconstructed through art, archives, and testimonies

Article Title: Analysis of Italian paintings reveals the cultural and culinary significance of the thorny oyster, combining with other historical texts and testimonies to uncover its "forgotten history"

Article References: Analysis of Italian paintings reveals the cultural and culinary significance of the thorny oyster, combining with other historical texts and testimonies to uncover its "forgotten history". (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: thorny oyster, Spondylus gaederopus, Italian paintings, Mediterranean Sea, marine historical ecology, PLOS One, food history, invasive species, Spondylus spinosus, art history, bivalves, cultural heritage

The authors, writing in the journal’s Geriatric Medical Classics series, chose the painting precisely because it invites a clinical misreading. The figure seems to embody what geriatricians call social frailty, a state in which older adults lose social contact, roles and resources, and which research has shown to predict incident disability. Yet the documented history of the picture shows that it is not a portrait of one man’s condition at all. It is a figure type, reworked across a decade, drawn from multiple models and literary sources, and animated by religious and poetic intentions that have nothing to do with the clinical categories a modern viewer brings to it. The failure of the clinical reading, the authors argue, is instructive in itself.

The canvas reworks Van Gogh’s own lithograph of November 1882, one of several earlier works he took up again in 1890 while recovering at the asylum, after spending the winter copying other artists’ prints. The pose itself predates that print: the artist first drew it in 1881 with a different model. In The Hague he returned to the composition with two sitters, one of them Adrianus Jacobus Zuyderland, a veteran living in the Dutch Reformed Old Men’s and Women’s Home. Art historians have linked the attitude to Charles Dickens’s illustrated Christmas books and to English prints of aged pensioners, probably including Hubert von Herkomer’s The Last Muster. In 1883 Van Gogh also used the same pose for young women. With the face hidden by the man’s fists, what the painting shows is a figure type rather than a record of Zuyderland’s state of mind.

Van Gogh’s own account of the work confirms how far it sits from clinical observation. Sending his brother Theo the first proof of the lithograph, he described the unutterably moving quality of an old man sitting quietly by his hearth as evidence of something on high. Weeks later he named the poem he had in mind: Thomas Moore’s Oft, in the stilly night, whose speaker, having outlived his friends, feels like one who treads alone in some banquet-hall deserted. Consolation and bereavement are both present in the artist’s own framing. The 1890 canvas, executed in the heavy brushwork of his late style, also carries the painter’s own feeling. As the gerontologists Heta Kauppinen and Patricia McKee argued in an earlier study cited by the authors, painters are not illustrators of gerontological theory, and treating them as such distorts both the art and the science.

Even the identity of the model undermines the solitary reading. Zuyderland was a paid and regular sitter who appears in dozens of Hague drawings wearing a top hat and long coat, smoking a pipe, reading or saying grace. Van Gogh praised his old, lively face. Zuyderland, then 72, lived to 87. A clinician shown only the 1890 painting would judge the man lonely and withdrawn; a clinician shown Zuyderland in his top hat would judge him robust. Neither judgement would constitute evidence, and the painting itself cannot settle the question. No window indicates whether it is day or night. The heavy boots are as consistent with a recent return from outdoors as with remaining indoors. Nothing in the image establishes whether anyone visits or speaks to the sitter, whether he goes out, or whether his distress, if any, reflects grief, poverty, illness or prayer.

This is where the essay turns from art history to measurement. Makizako and colleagues, in a widely cited 2015 study, showed that social frailty predicts incident disability in community-dwelling older adults, and they operationalised the construct with five questions: going out less often than a year earlier, rarely visiting friends, feeling unhelpful to family or friends, living alone, and not talking with anyone every day. None of these items can be inferred from posture or facial expression. Each must be asked, and several are informative only when repeated over time. A single image, like a single glance in a clinic, cannot supply them.

The five questions also point in different clinical directions, the authors note. Living alone and the absence of daily conversation describe the structure of a person’s social network, and they call for attention to contact, support and services. Going out less often and feeling unhelpful to others, by contrast, describe withdrawal and the loss of social roles, and they call for attention to participation and purpose. The painting cannot distinguish between these dimensions, and neither can a clinician who does not ask. The answers must also be read alongside the rest of the assessment, because withdrawal may reflect depression, cognitive decline, hearing loss or reduced mobility as much as a shrinking network, and each of those conditions can in turn deepen isolation. A patient who cannot hear the telephone may appear to have contact while being effectively cut off from it.

The essay situates the problem within comprehensive geriatric assessment, the structured multidimensional evaluation that measures gait, grip strength, cognition and nutrition with validated instruments. The social domain, by contrast, is often judged by impression, and the Van Gogh case demonstrates exactly why that impression is unreliable. Writing previously in the same journal, Sai Shreya and Harshil Sai drew on Rembrandt’s portrayals of ageing to argue that geriatric practice must hold a diagnostic and a human gaze together. Pehlivan and Doğu push the argument further: for social frailty even that dual gaze is insufficient, because the facts that matter are visible to neither gaze. Informants can mislead in the same way as appearances. A relative who brings the patient to clinic may be the only regular contact, and being accompanied on the day of the appointment says nothing about the rest of the week.

Moore’s poem also suggests when the relevant facts change. Its speaker is not neglected but bereaved, the last survivor of his circle, and this points to a pattern that clinicians can anticipate. In late life, a social network often contracts at identifiable transitions rather than gradually: the death of a spouse or friend, a move of home, entry to long-term care, or discharge from hospital. A single drawing of Zuyderland, like a single clinic visit, can support conclusions that the person’s circumstances do not warrant. The remedy the authors propose is correspondingly practical rather than philosophical. The five screening questions take little time and belong in the social history of every comprehensive geriatric assessment, including the assessment made before hospital discharge, where the risk of an abrupt contraction of support is highest.

A positive answer, the authors stress, should prompt further enquiry rather than a label: whether the person feels lonely, whether the change is recent, and what exactly has been lost. The answers should be recorded in structured form and reviewed at subsequent visits and at each of the recognised transitions, so that change over time, rather than a single observation, becomes the object of assessment. The lesson of the painting, then, is not that Van Gogh painted social frailty, but that he painted something clinicians are predisposed to read as social frailty, and that this predisposition is itself a source of error. In an era when loneliness is increasingly treated as a medical risk factor, the essay is a reminder that the most important information about an older person’s social world is not on display in their posture or their face. It has to be asked for, recorded, and asked for again.

Subject of Research: Social frailty assessment in older adults and the limits of clinical observation, illustrated through Van Gogh's painting

Article Title: Through Van Gogh's eyes: social frailty and the limits of clinical seeing

Article References: Pehlivan, M., & Doğu, B. B. (2026). Through Van Gogh's eyes: social frailty and the limits of clinical seeing. European Geriatric Medicine. https://doi.org/10.1007/s41999-026-01625-5

Image Credits: AI Generated

DOI: 10.1007/s41999-026-01625-5

Keywords: social frailty, Van Gogh, loneliness, comprehensive geriatric assessment, older adults, geriatric medicine, medical humanities, art history, ageing, disability risk, social networks, clinical observation

The idea of a canon, the set of works and figures a field treats as canonical, has always been contested in art history. Scholars such as Donald Preziosi and Eric Fernie documented how the discipline’s methods were shaped by particular institutions, and James Guillory’s work on literary canon formation showed how cultural capital accumulates around certain texts through institutional mechanisms. What Kocager and Yetişkin add is the observation that these mechanisms are now partly encoded in software. When a deep neural network classifies artistic styles, when a computer vision system retrieves visually similar paintings, or when a machine learning model quantifies creativity in an artist’s network, it is not merely processing images. It is reproducing and amplifying judgments about what counts as art, which styles matter, and whose heritage deserves digitization in the first place.

The technical lineage of this transformation stretches back further than the current deep learning boom. The authors trace early computational forays into the humanities to the 1990s, including machine learning systems applied to typologies of archaeological ceramics. By the mid-2010s, convolutional neural networks had transformed the field. Researchers demonstrated that binarized features derived from deep networks could classify artistic styles with remarkable accuracy, and systems were built to search vast databases of paintings by visual similarity. Computer-assisted analysis of brushstrokes in van Gogh’s works showed how digital image processing could extract visible features without human supervision, while studies applying optical techniques to works by Jan van Eyck and Robert Campin hinted at how algorithms could contribute to questions of perspective and attribution that had occupied art historians for generations.

Today, the methodological repertoire is broad. Surveys of computational methods for iconic image analysis document approaches ranging from pattern extraction and recognition in paintings and drawings to deep learning perspectives on beauty, sentiment, and remembrance in art. Some researchers have proposed creative adversarial networks that learn about styles and then deliberately deviate from style norms to generate novel images, prompting fierce debate about whether machines can be creative at all. Others have argued, as computer graphics researcher Aaron Hertzmann does, that computers do not make art, people do, and that the framing of AI systems as autonomous creators is itself a category error. Meanwhile, scholars in the digital humanities have explored how computational methods reshape the transformation of information into knowledge, and how interdisciplinary brokering between computer scientists and humanities scholars actually works in practice.

What makes the new study distinctive is its insistence that these technical developments cannot be understood apart from their social and political context. Drawing on traditions in science and technology studies, including Sheila Jasanoff’s work on the co-production of science and social order and Donna Haraway’s account of situated knowledges, the authors treat AI-assisted art history as a site where classifications and consequences intertwine. Geoffrey Bowker and Susan Leigh Star famously showed that classification systems are never innocent; they sort people and things into categories that carry material effects. Algorithmic canonization extends that insight to the art world: the datasets used to train models, the metadata attached to digitized collections, and the objectives chosen for machine learning systems all embed prior judgments about artistic value, and those judgments are then scaled and standardized in ways no individual curator or historian could achieve.

The empirical heart of the study is a systematic analysis of its 180-publication corpus across three dimensions: historical development, methodological orientations, and patterns of knowledge production. The multistage selection process, managed through a curated bibliographic database, allowed the authors to track who is publishing what, where, and with which conceptual ambitions. The findings reveal what the authors call a significant asymmetry. In the literature they examined, Asia appears mostly in association with data production and technical applications, while institutional structures centered in Europe and North America dominate conceptual framework building and theoretical discussion. In other words, the raw material for AI-driven art history increasingly comes from Asian collections and datasets, but the interpretive frameworks that determine what that material means are being constructed elsewhere.

This division of labor matters because it echoes long-standing critiques of how knowledge is produced in a globalized but unequal academic system. Related work in AI & Society has described the coloniality of experiments in art and AI, arguing that such experiments often proceed as if art history were a universal, placeless enterprise, and has examined cognitive imperialism in AI systems, proposing indigenous epistemologies as counterweights to embedded bias. Community-centered studies of text-to-image models in South Asia have documented how AI’s regimes of representation misrecognize the very populations they depict. Kocager and Yetişkin’s contribution is to show that a parallel dynamic operates in the apparently benign domain of art historical research, where the digitization of Asian heritage feeds computational pipelines whose theoretical framing remains Western.

Crucially, however, the authors resist the temptation to explain everything through a simple West-versus-Asia dichotomy. Their analysis emphasizes that Asia is not a monolith but harbors different centers and spheres of knowledge production, each with its own institutional configurations, research traditions, and technological capacities. Studies comparing Chinese and Western art history through big data approaches, for example, represent a distinct line of inquiry that cannot be reduced to a peripheral role. By positioning Asia not as a comparative object of study but as an analytical lens, the authors aim to reveal the inequalities in the existing knowledge production order from a vantage point that those inequalities would otherwise obscure. This methodological move follows broader arguments in feminist and postcolonial philosophy of science that the view from a marginalized position can expose assumptions invisible from the center.

The stakes extend beyond academia. As the Stanford AI Index documents the accelerating industrial scale of artificial intelligence, museums, auction houses, and cultural institutions are adopting computational tools for cataloging, authentication, and curation. When such tools determine which works are retrieved in a search, which attributions are flagged as plausible, or which styles are deemed similar, they participate in assigning value in the postdigital realm, a process scholars have already linked to canon formation and cultural heritage management. If the training data overrepresents certain regions, periods, or media, the resulting systems will systematically elevate some traditions and marginalize others, not through any explicit decision but through the accumulated weight of what was digitized, labeled, and learned. The authors’ framework gives curators, historians, and developers a vocabulary for interrogating these effects before they harden into a new, algorithmically enforced canon.

The study, which forms part of Kocager’s doctoral research at Istanbul Technical University conducted under Yetişkin’s supervision and supported by the TÜBİTAK 2211-A National PhD Scholarship Program, ultimately calls for a more pluralistic and critical engagement between artificial intelligence and art history. That means, at a minimum, attending to whose datasets train the models, whose categories structure the classifications, and whose institutions hold the authority to interpret results. It also means recognizing that technical choices, from feature extraction methods to similarity metrics, are interpretive commitments in disguise. As AI systems become embedded in the infrastructure of cultural memory, the question is no longer only whether machines can analyze art, but who gets to decide what the analysis means, and whose art history the algorithms will write. The concept of algorithmic canonization is offered as a starting point for answering those questions before the canon closes silently, one training set at a time.

Subject of Research: The role of artificial intelligence in canon formation and knowledge production in art history

Article Title: Algorithmic canonization: AI and art history through an Asian lens

Article References: Kocager, U., & Yetiskin, E. (2026). Algorithmic canonization: AI and art history through an Asian lens. AI & SOCIETY. https://doi.org/10.1007/s00146-026-03361-7

Image Credits: AI Generated

DOI: 10.1007/s00146-026-03361-7

Keywords: artificial intelligence, art history, algorithmic canonization, digital humanities, knowledge production, Asia, computer vision, deep learning, canon formation, science and technology studies, cultural heritage, AI & Society