NEANDERTHAL FINGER FLUTINGS, EUROPE’S OLDEST INTENTIONAL MARKS?

La Roche-Cotard manor house, France. Internet image, public domain.

In the ever proceeding scramble to identify the earliest, or oldest, rock art, we have another claim, this time from Europe. In the category of finger marks may I have the envelope please? And our winner is - - finger fluting on the cave walls of La Roche-Cotard left there by Neanderthals.

La Roche-Cotard finger fluting. Image from sci.news.

“The oldest known engravings in Europe, discovered in a French cave sealed up for tens of thousands of years, likely weren’t crafted by modern humans but rather Neanderthals, a new study finds. Within the cave of La Roche-Cotard 150 miles (240 kilometers) southwest of Paris, the researchers analyzed a series of non-figurative markings thought to be made by ancient human fingers, according to a study published – in the journal PLOS One. The cave had been sealed up by sediments until the late 19^th century. Modern excavations at the site have yielded numerous stone tools whose style is associated with the Neanderthals, suggesting that they created the art.” (Killgrove 2023) In addition to the style of stone tools the investigators used hard dating to infer the age of the marks.

The finger marks themselves were not dated, but optical stimulated luminescence dating told the investigators when the cave became inaccessible due to sedimentation. “OSL dating indicates that the sediment deposition closed the cave > 51 ka (95% confidence) ago, or at 57 ± 3 ka (68% confidence interval). This age makes access to the cave interior by anatomically modern humans (AMH) highly unlikely, as we believe that evidence for their arrival in Western Europe prior to 45 ka - is not yet demonstrated. The non-figurative engraved marks at La Roche-Cotard are necessarily older than 57 ± 3 ka, and can be, therefore, confidently stated to be of Neanderthal origin.” (Marquet, Jean-Claude et al., 2023) This adds even more proof of the cognitive sophistication of our hominin relatives.

La Roche-Cotard finger fluting. Image from sci.news.

While the term ‘graphic productions’ may be a little overly optimistic for the collections of markings left on the cave wall, they marks were made intentionally and apparently by hominins, not cave bears or other fauna.“The graphic productions identified on the walls of La Roche-Cotard demonstrate a deliberate creative process visible in the spatial arrangement of the engraved marks on the cave wall. This is perhaps one of the most remarkable aspects evidenced by the creative ensemble at La Roche-Cotard. As discussed above, there is little graphic evidence associated with Neanderthals, and that is mainly on mobile objects (pebbles, slabs, bones…), rather than walls. In contrast, the walls of La Roche-Cotard testify to something different: the frequent repetition of thoughtful gestures, organized in space both on the wall surfaces and with respect to the cave as a whole.” (Marquet, Jean-Claude et al., 2023) I cannot go quite as far as Marquet’s last sentence in describing the marks, but I applaud his enthusiasm.

La Roche-Cotard finger fluting. Image from sci.news.

Now, of course, we have to address the question of whether finger-fluting is art and deserves to be lumped in with rock art. In the case of RockArtBlog I say yes. It is intentional modification to the cave wall in the same way that a magnificent painted animal on a cave wall is and that is the definition I am using.

NOTE: Some images in this column were retrieved from the internet with a search for public domain photographs. If any of these images are not intended to be public domain, I apologize, and will happily provide the picture credits if the owner will contact me with them. For further information on these reports you should read the original reports at the sites listed below.

REFERENCES:

Killgrove, Kristina, 2023, Neanderthals created Europe’s oldest ‘intentional’ engravings up to 75,000 years ago, study suggests, 21 June 2023, LiveScience.com. Accessed online 10 September 2025.

Marquet, Jean-Claude et al., 2023, The earliest unambiguous Neanderthal engravings on cave walls: La Roche-Cotard, Loire Valley, France, 21 June 2023, PLOS One, https://doi.org/10.1371/journal.pone.0286568. Accessed online 8 September 2025.

 

 

TRAINING AI TO DETERMINE THE GENDER OF THE MAKERS OF FINGER FLUTING ON CAVE WALLS:

Finger fluting at Gargas Cave, France. Image from Clottes, 2002.

We are all probably aware of the existance finger fluting in caves, it is found all over the world, but it has always been somewhat peripheral to the subject of cave art itself. It is, however, purposeful markings made by people on the cave walls so it needs to be covered in any consideration of cave art. Various examples have been attributed to Neandertals, as well as Homo sapiens men, women and children. Now, a team in Australia is using artificial intelligence to try to clarify the makers of these marks.

“Flutings have the potential to reveal information about age, sex, height, handedness and idiosyncratic markmaking choices among unique individuals who form part of larger communities of practice. However, previous methods for making any determination about the individual artist from finger flutings have been shown to be unreliable4. Accordingly, we propose a novel digital archaeology approach to begin understanding this enigmatic form of rock art by leveraging machine learning (ML) as a tool for uncovering patterns from two datasets, one tactile and one virtual, collected from a modern population. We aimed to determine whether ML can reveal subtle differences in the sex of the artist based on their finger-fluted images.” (Jalandoni et al. 2025:1) In other words they will attempt to have machine learning programs learn to distinguish information like gender and age by analyzing finger fluting created by volunteers. If successful, this could then be applied to finger fluting in cave walls to learn more about the persons who originally created the marks.

Finger fluting attributed to Neandertals, Noire Valley, France. Image from Jean Claude Marquet.

“Experiments were conducted - both with adult participants in a tactile setup and using VR headsets in a custom-built program – to explore whether image-recognition methods could learn enough from finger fluting images made by modern people to identify the sex of the person who created them.” (Lock and Egan 2025:1) The team had participants actually make finger flutings in clay as well as virtually while being videotaped. “Two controlled experiments with 96 adult participants were conducted with each person creating nine flutings twice: once on a moonmilk clay substitute developed to mimic the look and feel of cave surfaces and once in virtual reality (VR) using Meta Quest 3. Images were taken of all the flutings, which were then curated and two common image-recognition models were trained on them. (Lock and Egan 2025:1-2)

Disappointingly, the tests did not produce reliable results. “The VR images did not yield reliable sex classification; even when accuracy looked acceptable in places, overall discrimination and balance were weak. But the tactile images performed much better. ‘Under one training condition, models reached about 84% accuracy, and one model achieved a relatively strong discrimination score.’ Dr. Tuxworth said. However, the models did learn patterns specific to the dataset; for example, subtle artifacts of the setup, rather than robust features of fluting that would hold elsewhere, which meant there was more work to be done.” (Lock and Egan 2025:1-2) Doctor Gervase Tuxworth is one of the experimental team that conducted this study. His statement suggests that the test results were highly variable.

Paleolithic finger fluting from Rouffignac Cave, France. Online image, public domain.

“Overall, the deep learning models achieved high accuracy during training, with AUC values exceeding 0.85 for certain tactile image conditions. These results suggest that the models effectively learned patterns within the tactile dataset and demonstrated strong discrimination between male and female-generated finger fluting images. However, the relatively lower AUC values for virtual images, coupled with their unstable test accuracy, indicate that they do not provide sufficiently distinct features for reliable sex classification. This discrepancy highlights the greater robustness of tactile images over virtual images in capturing relevant classification features. Despite the promising performance on tactile images, deep learning models exhibited a pronounced disparity between training and test performance. While training accuracy consistently increased, reaching near-perfect levels in the later epochs, test accuracy remained unstable and showed no substantial improvement over time. This pattern indicates overfitting, where the models effectively learn dataset-specific features but fail to generalize to unseen test data.” (Jalandoni et al. 2025:10) I find the previous paragraph somewhat confusing. It states “accuracy consistently increased, reaching near-perfect levels” and “accuracy remained unstable and showed no substantial improvement” in two contiguous sentences. In any case, the team did not get reliable results.

Finger fluting made by children, Rouffignac Cave, France. Online image, public domain.

There are a number of possible sources of inaccuracy in the test results.“The instability in test accuracy further suggests that the models struggle to extract robust and generalizable patterns from the finger fluting images, ultimately limiting their reliability for sex classification. A possible contributing factor to this challenge could be individual variation in hand size and fluting characteristics. For example, some females may have larger hands and exhibit stronger fluting patterns resembling those of males, while some males may have smaller hands and display lighter, less pronounced fluting strength. This variability could confuse the model, making it difficult to accurately differentiate between sexes and ultimately hindering its performance on the test set. These results underscore the critical need to increase the dataset size to alleviate overfitting and improve the model’s generalizability. Moreover, the inherent variability in finger fluting images may impose fundamental limitations on the feasibility of using deep learning for sex classification, suggesting that alternative approaches or additional contextual data may be necessary to enhance classification accuracy. The limited success of the tactile data in sex prediction underscores the importance of material-based approaches in understanding finger flutings. While the VR data failed to provide useful results, it opens up new and exciting possibilities for exploring the dynamic aspects of fluting and artistic intent in the future. While a modest achievement, this study highlights the potential of ML to enhance traditional archaeological methods”. (Jalandoni et al. 2025:10) Not every try is guaranteed success.

Koonalda Cave finger flutings, Australia. Photograph Robert Bednarik, 1979.

So, this test did not manage to display reliable accuracy, too many variables in the creation of finger fluting seemingly overwhelmed the software. Also, the experiment apparently did not include children, and it is thought that much finger fluting, at least in European cave contexts, was created by children. If successful, this project would have been a really wonderful development but, alas, it was not. Better luck next time.

NOTE: Some images in this column were retrieved from the internet with a search for public domain photographs. If any of these images are not intended to be public domain, I apologize, and will happily provide the picture credits if the owner will contact me with them. For further information on these reports you should read the original reports at the sites listed below.

REFERENCES:

Andrea Jaladoni, Robert Haubt, Calum Farrar, Gervase Tuxworth , Zhongyi Zhang , Keryn Walshe and April Nowell, 2025, Using digital archaeology and machine learning to determine sex in finger flutings, Scientific Reports, 15:34842. https://doi.org/10.1038/s41598-025-18098-4. Accessed online 12 October 2025.

Lock, Lisa, and Robert Egan, 2025, VR experiments train AI to identify ancient finger-fluting artists, 16 October 2025, The GIST, by Griffith University, https://phys.org/news/2025-10-vr-ai-ancient-finger-fluting.html.

TRAINING AI TO DETERMINE THE GENDER OF THE MAKERS OF FINGER FLUTING ON CAVE WALLS:

Finger fluting from Gargas Cave, France. Photograph 2002 by Jean Clottes.

A couple of weeks ago I wrote again about determining the gender of the maker of a handprint by ratios of finger lengths. Well, staying with the hand, this column is about a project that attempted to train a maching learning (ML) program to determing the gender of the makers of finger fluting. We are all probably aware of finger fluting in caves, it is found all over the world, but it has always been somewhat peripheral to the subject of cave art itself. It is, however, purposeful markings made by people on the cave walls so it needs to be covered in any consideration of cave art. Various examples have been attributed to Neandertals, as well as Homo sapiens men, women and children. Now, a team in Australia is using artificial intelligence to try to clarify the makers of these marks.

Finger fluting believed to be by children, Rouffignac Cave, France. Internet image, public domain.

“Flutings have the potential to reveal information about age, sex, height, handedness and idiosyncratic markmaking choices among unique individuals who form part of larger communities of practice. However, previous methods for making any determination about the individual artist from finger flutings have been shown to be unreliable4. Accordingly, we propose a novel digital archaeology approach to begin understanding this enigmatic form of rock art by leveraging machine learning (ML) as a tool for uncovering patterns from two datasets, one tactile and one virtual, collected from a modern population. We aimed to determine whether ML can reveal subtle differences in the sex of the artist based on their finger-fluted images.” (Jalandoni et al. 2025:1) In other words they will attempt to have machine learning programs learn to distinguish information like gender and age by analyzing finger fluting created by volunteers. If successful, this could then be applied to finger fluting in cave walls to learn more about the persons who originally created the marks.

Neanderthal finger fluting, Noire Valley, France. Photograph by Jean Claude Marquet.

“Experiments were conducted - both with adult participants in a tactile setup and using VR headsets in a custom-built program – to explore whether image-recognition methods could learn enough from finger fluting images made by modern people to identify the sex of the person who created them.” (Lock and Egan 2025:1) The team had participants actually make finger flutings in clay as well as virtually while being videotaped. “Two controlled experiments with 96 adult participants were conducted with each person creating nine flutings twice: once on a moonmilk clay substitute developed to mimic the look and feel of cave surfaces and once in virtual reality (VR) using Meta Quest 3. Images were taken of all the flutings, which were then curated and two common image-recognition models were trained on them. (Lock and Egan 2025:1-2)

Additional finger fluting from Rouffignac Cave, France. Internet image, public domain.

Disappointingly, the tests did not produce reliable results. “The VR images did not yield reliable sex classification; even when accuracy looked acceptable in places, overall discrimination and balance were weak. But the tactile images performed much better. ‘Under one training condition, models reached about 84% accuracy, and one model achieved a relatively strong discrimination score.’ Dr. Tuxworth said. However, the models did learn patterns specific to the dataset; for example, subtle artifacts of the setup, rather than robust features of fluting that would hold elsewhere, which meant there was more work to be done.” (Lock and Egan 2025:1-2) Doctor Gervase Tuxworth is one of the experimental team that conducted this study. His statement suggests that the test results were highly variable.

“Overall, the deep learning models achieved high accuracy during training, with AUC values exceeding 0.85 for certain tactile image conditions. These results suggest that the models effectively learned patterns within the tactile dataset and demonstrated strong discrimination between male and female-generated finger fluting images. However, the relatively lower AUC values for virtual images, coupled with their unstable test accuracy, indicate that they do not provide sufficiently distinct features for reliable sex classification. This discrepancy highlights the greater robustness of tactile images over virtual images in capturing relevant classification features. Despite the promising performance on tactile images, deep learning models exhibited a pronounced disparity between training and test performance. While training accuracy consistently increased, reaching near-perfect levels in the later epochs, test accuracy remained unstable and showed no substantial improvement over time. This pattern indicates overfitting, where the models effectively learn dataset-specific features but fail to generalize to unseen test data.” (Jalandoni et al. 2025:10) I find the previous paragraph somewhat confusing. It states “accuracy consistently increased, reaching near-perfect levels” and “accuracy remained unstable and showed no substantial improvement” in two contiguous sentences. In any case, the team did not get reliable results.

Finger fluting in Koonalda Cave, Australia, Photograph 1979, by Robert Bednarik. 

There are a number of possible sources of inaccuracy in the test results. “The instability in test accuracy further suggests that the models struggle to extract robust and generalizable patterns from the finger fluting images, ultimately limiting their reliability for sex classification. A possible contributing factor to this challenge could be individual variation in hand size and fluting characteristics. For example, some females may have larger hands and exhibit stronger fluting patterns resembling those of males, while some males may have smaller hands and display lighter, less pronounced fluting strength. This variability could confuse the model, making it difficult to accurately differentiate between sexes and ultimately hindering its performance on the test set. These results underscore the critical need to increase the dataset size to alleviate overfitting and improve the model’s generalizability. Moreover, the inherent variability in finger fluting images may impose fundamental limitations on the feasibility of using deep learning for sex classification, suggesting that alternative approaches or additional contextual data may be necessary to enhance classification accuracy. The limited success of the tactile data in sex prediction underscores the importance of material-based approaches in understanding finger flutings. While the VR data failed to provide useful results, it opens up new and exciting possibilities for exploring the dynamic aspects of fluting and artistic intent in the future. While a modest achievement, this study highlights the potential of ML to enhance traditional archaeological methods”. (Jalandoni et al. 2025:10) Not every try is guaranteed success.

So, this test did not manage to display reliable accuracy, too many variables in the creation of finger fluting seemingly overwhelmed the software. Also, the experiment apparently did not include children, and it is thought that much finger fluting, at least in European cave contexts, was created by children. If successful, this project would have been a really wonderful development but, alas, it was not to be. Better luck next time.

NOTE: Some images in this column were retrieved from the internet with a search for public domain photographs. If any of these images are not intended to be public domain, I apologize, and will happily provide the picture credits if the owner will contact me with them. For further information on these reports you should read the original reports at the sites listed below.

REFERENCES:

Andrea Jaladoni, Robert Haubt, Calum Farrar, Gervase Tuxworth , Zhongyi Zhang , Keryn Walshe and April Nowell, 2025, Using digital archaeology and machine learning to determine sex in finger flutings, Scientific Reports, 15:34842. https://doi.org/10.1038/s41598-025-18098-4. Accessed online 12 October 2025.

Lock, Lisa, and Robert Egan, 2025, VR experiments train AI to identify ancient finger-fluting artists, 16 October 2025, The GIST, by Griffith University, https://phys.org/news/2025-10-vr-ai-ancient-finger-fluting.html.

 

57,000 YEAR OLD NEANDERTHAL CAVE MARKINGS IN LA ROCHE-COTARD:

Cave of La Roche-Cotard, France. Online image, public domain.

On 19 November 2022 I posted a column titled "A Neanderthal Mystery – The Mask of La Roche-Cotard." This discussed a mysterious artifact from that cave, attributed to Neanderthal occupation comprising a flake of flint shaped like a face with a piece of bone shoved through a natural hole looking somewhat like eyes (Faris 2022). In this column I am presenting a study (Marquet et al. 2023) that discusses finger flutings and other marks made in La Roche-Cotard by Neanderthals dated to approximately 57,000 BCE.

Pillar chamber, cave of La Roche-Cotard, France. Photogrammetry by Y. Egels, journal.pone.

“Today, the cave of La Roche-Cotard comprises four main chambers extending ESE-WNW for 33 m: the Mousterian Gallery, the Lemmings Chamber, the Pillar Chamber and the Hyena Chamber. In the back of the Hyena Chamber, collapse of the ceiling prevents the determination of the exact extent of the ancient cavity.” (Marquet et al. 2023) And now we have to wonder what might be behind the collapsed ceiling.

Circular panel, La Roche-Cotard, France. Image from journal.pone.

“The site of La Roche-Cotard is in Indre-et-Loire, in the commune of Langeais, France. Discovered in January 1912, the cave is on the south-facing slope on the right bank of the Loire. The entrance is at the back of a small rocky cirque, only a few meters above the top of the river’s modern embankment. The cave comprises a narrow gallery, a tunnel some 10 m (33 feet) long and three wider chambers, extending around 40 m (131 feet) in all.” (De Lazaro 2023)

Dotted panel, La Roche-Cotard, France. Image from journal.pone.

“Following human occupation, the cave was completely sealed by cold-period sediments, which prevented access until its discovery in the 19^th century and first excavation in the early 20^th century. - In 1846, La Roche-Cotard cave entrance was exposed during quarrying and in 1912, the site owner François d’Achon excavated almost all the inner sedimentary deposits. Only Mousterian lithic artefacts were discovered within the cave; no later-period material was found. Subsequent excavation, in the 1970s and from 2008 onwards, identified three additional loci close to the cave.” (Marquet et al. 2023) In Europe, the Mousterian industry is associated with Neanderthal occupation.

Cave of La Roche-Cotard, France. Online image, public domain.

“The team first dated samples of cave sediment using a technique called optically stimulated luminescence (OSL) dating, which determines the time since sedimentary grains were last exposed to daylight. They concluded that the cave had been sealed off by sediment brought in by the flooding of the Loire around 57,000 years ago, well before Homo sapiens made their way into the region. Stratigraphic dating yielded an earlier date of around 75,000 years ago, which would make this "the oldest decorated cave in France, if not Europe," the authors wrote. Since the only stone tools found in the cave over the last century are those associated with Neanderthals, that provides two lines of evidence in support of the hypothesis that Neanderthals created the finger flutings.” (Ouellette 2023) In other words, if the only evidence of occupation of this cave is Neanderthals, then the wall markings must be Neanderthal as well.

Undulated panel, La Roche-Cotard, France. Image from journal.pone.

“Marquet et al. also modeled the entire cave with photogrammetry to more precisely locate the engravings and to carefully distinguish between the different kinds of traces. They focused on the suspected finger flutings for further analysis, then drew reproductions of the panels and carefully noted their detailed observations. The team concluded that the marks were deliberate, organized, and intentional shapes—arch-shaped tracings, for example, or two contiguous tracings forming sinuous lines.” (Ouellette 2023) Organized and intentional shapes created before anatomically Human entrance into Europe would only be attributed to Hominin presence, in other words, Neanderthal.

Triangular panel, La Roche-Cotard, France. Image from journal.pone.

“The numerous marks on the soft surface layers of the walls of have been categorized according to origin: those made by humans must be distinguished from those made by animals, as well as those arising from local geochemical alteration (surface dissolution, disintegration, dehydration), and minor chemical deposits (concretions). Animal claw marks, attributable to Ursus sp., Meles sp. and other species, can be identified by their characteristic spacing and incision angle. But alongside these numerous, randomly distributed animal scratch marks, there are also a number of elongated or dotted, spatially organized marks. These organized marks are found only on the 13 m long north-east wall of the pillar chamber (shown with a blue line in. They have distinct geometric shapes and are often grouped into panels separated by groups of smaller marks. Analysis based on the width, incision angle and depth of 116 marks revealed two statistically distinct groups: 32 with features consistent with claw marks, and 84 most likely of anthropogenic origin. Those identified as claw marks are thinner, deeper and have a V-shaped cross-section, whereas the presumed ancient spatially organized marks are mostly wider, shallower, and U-shaped, consistent with the morphology of a fingertip or similarly shaped tool. However, the rectangular panel is clearly separated, first from the two panels made with fingers and secondly separated from the claw marks.” (Marquet et al. 2023) Not only do we have the marks left by Neanderthals, we have marks left by bears and badgers – bear and badger rock art?

Cave bear (Ursus speleus). Image by Patrick Burgler.

European badger (Meles meles). Online image, public domain.

“The attribution to Neanderthal of the graphic productions at La Roche-Cotard pays tribute to this lost humanity, whose role in the biological and cultural evolution of humans is undergoing profound revision. In terms of culture, we now have a better understanding of the plurality of Neanderthal activities, attesting to elaborate and organized social behaviours that show no obvious differences from those of their contemporaries, Anatomically Modern Humans, south of the Mediterranean.” (Marquet et al 2023)

Note the last line of that quote “organized social behaviours that show no obvious differences from those of their contemporaries, Anatomically Modern Humans, south of the Mediterranean.” I am personally uncomfortable with the part about “no obvious differences” because I believe there are many obvious differences. From their tools, to their social interactions and personal adornment, we find traces of differences, but they are cultural differences. Notice I said cultural – because I do not think that any of them indicate differences in potential from those contemporaries. I believe that the Neanderthals had localized cultures in just the same way modern Human societies do. In other locations we have found Neanderthals using paint in caves, or incising petroglyphs into the rock with stone tools. In La Roche-Cotard their creative expression was to leave finger fluting.

NOTE: Some images in this posting were retrieved from the internet with a search for public domain photographs. If any of these images are not intended to be public domain, I apologize, and will happily provide the picture credits if the owner will contact me with them. For further information on these reports you should read the original reports at the sites listed below.

REFERENCES:

De Lazaro, Enrico, 2023, 57,000-Year-Old Neanderthal Engravings Discovered in France, 22 June 2023, https://sci.news. Accessed online 22 June 2023.

Faris, Peter, 2022, A Neandertal Mystery – The Mask of La Roche-Cotard, 19 November 2022, RockArtBlog, https://www.blogger.com.

Marquet, Jean-Claude et al., 2023, The earliest unambiguous Neanderthal engravings on cave walls: La Roche-Cotard, Loire Valley, France, 21 June 2023, https:journals.plos.org/plosone/. Accessed online 22 June 2023.

Ouellette, Jennifer, 2023, Could these marks on a cave wall be oldest-known Neanderthal ‘finger paintings’?, 21 June 2023, https://arstechnica.com. Accessed online 22 June 2023.