The southern Caucasus played overall a key role in human evolution, with the region of western Georgia (Imereti) being a major geographic corridor for human migrations during the Middle and Upper Paleolithic. It is also a prime location to study Neanderthal and modern human interactions during the Middle to Upper Paleolithic transition [1–5]. The study of the local Early Upper Paleolithic (EUP) and Upper Paleolithic (UP) sequences is critical to the understanding of how human populations responded to the climatic shifts during the Last Glacial [6, 7].

New research and excavations in this region since the mid-1990s show its importance as a possible route for the dispersal of AMH to northern Eurasia [1–3, 8–12]. Moreover, recent excavations with fine chronological and stratigraphic resolution indicate a discontinuous transition model between the Middle Paleolithic and the Early UP ca. 39,000–34,000 years ago with evidence of a chronological rupture between these two cultural traditions [5, 7, 13–19]. This suggests that the Greater Caucasus mountain range, which seems to have constituted a geographic-cum-cultural barrier for the migration of Neanderthals to the north, was crossed by AMH [14, 20]. Recent work also suggests that climate change around 40 Ka would have favoured the migration of AMH into this region [7, 10].

The local UP research (e.g., [13, 17–21]) had been mostly concerned with human adaptation to local circumstances reconstructed through environmental studies (e.g., palynology [22]) and reflected in hunting behaviors and the fauna prey remains [2, 23–30], as well as the developments and evolution of the chipped stone technology [13, 17]. Actual human remains are quite few [31].

Currently, the earliest Caucasian EUP dates derive mainly from sites on the northern slopes of the Greater Caucasus (Mezmaiskaya and Korotkaya) [10, 11] and those located on its southern slopes (Dzduzuana, Ortvale Klde, Bondi Cave, Aghitu-3 Cave) [3, 13, 32]. Most of those dates cluster around 39 Ka CalBP, yet more recent dating endeavours place the beginning of the UP at 46.7/43.6 Ka calBP [5]. It appears that the regional EUP assemblages from both the northern and southern Caucasus have similar techno-typological features. These EUP assemblages are rich in retouched and backed bladelets resembling more the contemporaneous Levantine Ahmarian than the European Early Aurignacian and the ‘Classic’ Levantine Aurignacian [7, 13, 14].

Personal ornaments and bone tools, engravings on objects and cave walls, and burial practices, are among the cultural features considered as reliable proxies for the emergence of symbolically mediated behaviour (SMB) [33–43]. Indeed, personal ornaments constitute a valuable archaeological category since a) they indicate shared aesthetic values and may serve as markers of social identity (be it a status [e.g., age-grade] or group [e.g. family, clan]; b) they have been used by a large number of ethnographically well-documented traditional societies combining both, their aesthetic and symbolic merits; c) they are common at UP sites, and d (they occur during this period in a great typological variety [44–58]. It is thus essential to try to assess the preferences in a regional selection of the raw materials, supports and shapes of the ornaments–if any–and compare it with other areas. Bone implements are well represented in most of the sites, with assemblages that comprise mainly simple/massive based points, hunting weapons, and bone awls, but also eye needles and personal ornaments [3, 11, 13, 18, 19, 28]. However, worked bone items and personal ornaments have contributed little to the characterization of the UP assemblages from Northern Caucasus (e.g., Mezmazkaia Cave [11]) and Southern Caucasus (e.g., Dzudzuana Cave [13]) as these studies portray mainly a typological approach, while technological and use-wear analyses are rare or missing all together.

Here we present an archaeozoological, technological and use-wear study of pendants from two UP Southern Caucasus assemblages, Dzudzuana Cave and Satsurblia Cave, located 30 km apart in the Imereti region, Georgia. The set encompasses specimens both from the EUP (Satsurblia layers B/V, B/IVb) and later UP (Dzudzuana Unit C; Satsurblia layers A/III, B/III, BIVa), from ca. 43/39 to 25.5/24.4 Ka calBP. The ornaments were made mostly on teeth by a perforation of the root to be suspended as pendants or attached to garments. Other specimens are made on bone. According to technological and experimental analyses (see below), both the manufacturing marks made during the preparation of the items and the use-wear traces indicate that the modified items served as personal ornaments.

While the chipped-stone techno-typology seems to demonstrate a local development of the region’s EUP entities, the bone tools and personal ornaments show similarities with comparable items from the European and Levantine Aurignacian and some sets from the initial UP of Central and Northern Asia. Such analogies suggest a link between the symbolic sphere of cultural entities in the Caucasus, Europe, the Levant, and other Asian regions during the early UP. Regarding the personal ornaments, the importance accorded to the red deer within the symbolic sphere of the Caucasus UP hunter-gatherers is highlighted by the selection of this taxa to fabricate almost 50% of the pendant assemblages. In comparison, this taxon comprises only 2% of the total NISP of the faunal remains in the studied layers at Dzudzuana [25], whereas at Satsurblia it includes c. 28% of the assemblage. The results of the personal ornaments studies point to the existence of anthropological and cultural ties between the Northern and Southern Caucasus UP populations, as has been previously suggested based on cross-regional sharing of lithic techno-typological characteristics [7].

The herein discussed assemblages of personal ornaments recovered from Dzudzuana and Satsurblia caves consist of a total of nineteen perforated or grooved teeth, eight perforated or grooved bones and one possibly antler fragment, also with a perforation (Table 1). We have not included in the study ‘decorated (drilled, incised, notched) bones, shells and pendants made on stone from Dzudzuana described in previous publications [13]. All the pendants from Dzudzuana were found in Unit C, one in sub-layer 3 and one in sub- layer 4 (Fig 2). The items from Satsurblia derive from area A (N = 3) and area B (N = 13) of the recent excavations. All pendants from area A have been recovered in layer A/III. Two pendants from area B were found in layer B/V, three in layer B/IVb, one in layer B/IVa, and seven in layer B/III. No permits were required for the described study, which complied with all relevant regulations.

The studied material is housed at the prehistory storage facilities of the Georgian State Museum (Tbilisi, Georgia) (Table 1). The taxonomic identification of the items is based on the comparative osteological collections of the National Natural History Collections, The Hebrew University of Jerusalem and the University of Haifa through prior research [52]. Published criteria were also consulted for taxonomic identification, e.g., Brown and Chapman [86] for red deer.

The distinct sexual dimorphism of red deer [87, 88], is also expressed in the shape and size of their canines [89]. Over the evolution of the family Cervidae, hornless ruminants predated the antlered ones. The size of the tusk-like upper canine teeth has tended to be inversely correlated with the size of the antlers, as if ‘holding on’ to the former compensated for the lack/small size of the latter. As the antlers became longer, the canines became shorter, eventually disappearing. While in most cervids they have been lost some species like red deer (Cervus elaphus) have retained vestigial canines [87].

As changes occur through life in the shape, root and size of the canines, the specimens were examined for age and sex, following the methods of d’Errico and Vanhaeren [90]. Apparently, male vestigial canines are broader than those of the females and with wear, the fully-grown shape in young males becomes triangular. Conversely, crowns of young females are pointed, and those of older specimens are rectangular. The roots of vestigial male canines are square or trapezoid while those of females are rectangular or V-shaped.

We recorded morphometric variables for each canine. These include occlusal wear stages, stages of root development, state of closure of the pulp cavity, and wear removal of the disto-lingual-cervical lobe. Metric variables include crown width, length and thickness, width and length of the occlusal wear facet, maximum width, apex width, root thickness and root length (Table 2).

For the description of the specimens’ modification, we followed the methodology of Barge-Mahieu et al. [91], White [44, 45, 92], Vanhaeren [93] and d’Errico and Rigaud [94], among others. We described the perforation process, dimensions, location, preparation modes and perforation techniques (e.g., diameter, shape, the distance between the tooth buccal and lingual edges, distance between the perforation and the root base).

Technological and use-wear analyses were conducted using both a stereomicroscope Leica S8APO with led light LZ, and an Olympus SZX16 with KZ1600 LED source (magnification: 10–115x). Stereomicroscope images were taken with an Olympus SC50 camera coupled to the microscope and recorded with Olympus CellSens software.

Personal ornaments are among the cultural features considered as reliable proxies for the emergence of symbolically mediated behaviour (SMB) and complex societies [34, 37–39, 42, 55–58]. This assumption does not detract from the fact that aesthetics had most probably also played a role in the production of personal ornaments, as can be observed in extant primeval and complex modern societies.

In the Caucasus, the technical and symbolic use of bone, antler, teeth and shell seem to appear abruptly at the onset of the UP–from ca. 39 Ka (or even earlier and see above) years ago onwards [7, 10, 13]. Just like the chipped-stone techno-typology of the local EUP, also the symbolic sphere of the Caucasian hunter-gatherer groups, expressed in their personal ornaments, suggests some links with the coeval UP from other areas of Eurasia.

It is not easy to precisely characterize the production of the UP personal ornaments in the Caucasus overall through its technical aspects. This is due to the lack of technical studies of large corpora in the relevant regions; the flexibility in the techniques employed: and the limited sample size of the so far known assemblages. Contrary to the presence of bone and antler tools, personal ornaments are documented in the pre-LGM archaeological record of the Caucasus only in a few sites and in small numbers. These are Mezmaiskaya in the north [7, 11], Dzudzuana and Satsurblia in the south [13, this paper], and the Armenian site of Agithu-3, where there are only perforated shells with no teeth or bone specimens [32].

No particular association was observed in Dzudzuana and Satsurblia between a type of pendant, its raw material and a precise production technique. We can thus assume that on the whole, the UP Caucasian groups have employed different techniques for the manufacture of the pendants, similar to those observed in the European and Levantine EUP and at the beginning of the UP in Central Asia. The methods employed in these areas were varied, showing technical flexibility with gouging and rotation extensively documented [7, 44, 45, 52, 94, 117, 118].

Nevertheless, other behavioural aspects related to personal ornaments can provide us with new comparative elements. Selecting particular species and anatomical parts has demonstrated both shared and divergent choices regarding the aesthetic–cum-symbolic set–personal ornaments and decorated bones–from Western Europe and the Levant in the Early UP [51, 52]. In this regard, red deer vestigial canines seem to have a special status among the UP societies of the Caucasus, a feature shared with its counterpart groups in the Levant and Western and Central Europe as well as those from Central and Northern Asia [45, 52, 101, 119]. This can also be because the vestigial canines enter the chewing process only marginally and remain largely not worn during the animal’s life, which makes them appear particularly uniform in their shape and symmetrical, adding to those teeth further value, i.e., ‘pleasing to the eye’ [55–58]. Besides the ten red deer vestigial canines analysed, six other specimens (one red deer incisor and five bone pendants) were modified imitating their shape and size (Fig 7). Thus, sixteen of the full set of studied pendants–more than half of the assemblage—are red deer vestigial canines whether real or fake. Interestingly, in Mezmaiskaya, four of the seven perforated teeth recorded from EUP (1C), and late UP layers (1A2, 1A1) are red deer vestigial canines, with two caprid incisors and one perforated bone imitating them in shape and dimensions [7, 11].

The significance accorded to the red deer among the pre-LGM UP groups in the Caucasus contrasts with its low importance in their subsistence. For example, in Dzudzuana cave of the nine perforated teeth, seven are of red deer. However, Dzudzuana red deer specimens represent 2% of the identified species of ungulates. In Satsurblia, out of ten teeth pendants five are of red deer. The frequencies of red deer at this site comprise only ca. 30% of the NISP in each layer. Among the teeth in Dzudzuana, no canines other than the perforated specimens were identified [25]. In Satsurblia only one canine was recovered, besides those shaped as pendants. The same is true for Mesmaiskaya where mammals assigned to size 2 (caprids) and size 4 (Bos/bison) represent ca. 40% of the NISP in layers 1C and 1A while red deer presence is much more restricted [11] (Fig 8).

The preference of one taxon and a particular tooth, namely the red deer vestigial canines, to make personal ornaments is a behavior shared by European, Levantine and Caucasian early UP groups. Perforated vestigial deer canines have been recently reported from Early UP in the Altaï mountains, in Central Asia e.g., Strashnaya [120], and Denisova [101], as well as from the North of China in Zhoukoudian Upper Cave [121]. Though the European hunter-gatherers exploited a large variety of teeth of diverse mammals, it appears that pierced red deer teeth were of importance and were worn by individuals traveling over long distances [122]. The apparent dissociation between animals whose meat was the staple food and animals whose teeth were used for ornaments is particularly marked in the case of red deer. The geographic distribution of red deer pendants in the European UP does not reflect the animals’ geographic distribution, because the pendants seem to have moved prior to the LGM beyond the extent of the red deer primary distribution areas [123, 124].

Cervus elaphus is one of the most abundant large mammal taxa in the European Late Pleistocene archaeological record [125, 126]. Although the red deer is an ecologically flexible species, it has been best adapted to temperate climate conditions and forested habitats [124]. Also in the Caucasus, red deer was present in EUP contexts [127]. Nevertheless, its frequencies in the archaeological record are anecdotal compared with that of caprids and, to a lesser extent, that of big bovids (Bos/Bison). According to currently available data, the latter faunal categories are the most common mammal species hunted and consumed in Caucasian UP sites, i.e., at Dzudzuana, Satsurblia, Mezmaiskaya, Ortvale Klde, Bondi Cave, and Hovk-1 [2, 11, 17–19, 27, 28] (Fig 8).

Apparently, prehistoric Eurasian societies had indeed a strong preference for the use of red deer canines as personal ornaments. Their presence in many prehistoric settlements, in different contexts, including single burials with dozens of those pendants in the UP [128], and in the Mesolithic [116, 129] as well as in extant ethnographic examples [130]–suggests that they possessed besides their aesthetic merit also a symbolic value for both Palaeolithic and post- Palaeolithic societies. Countless examples have been ethnographically observed of a particular animal special status within the symbolic world of extant hunter-gatherer societies [55–58, 131–133], suggested also for contexts from the Middle Palaeolithic [134] through the Mesolithic [135]. Yet, in most cases, these animals had seemingly an important nutritional value [136, 137] contra that of the red deer.

Still, the choice of C. elaphus vestigial canines could also be explained by the tooth’s particular rounded shape as well as its gloss and its tactile qualities [45]. Perhaps these were the reason for their imitation in different raw materials (bone and antler) by Palaeolithic hunter-gatherer groups in all Eurasian regions [7, 46, 107]. Similar qualities have been alleged for other raw materials used for ornaments like ivory, amber, and shells [45, 49, 138–141].

While it is tempting to argue for differences in the personal ornaments of the Caucasus between the EUP and the following UP assemblages, we should be cautious because the sample is relatively small. A shift has been evoked in the production of pendants at Mezmaiskaya. The pendants recovered from EUP layers (1C, 1B) were manufactured from a single species of teeth (Caucasian tur), as opposed to those from UP layers (1A1, 1A2) mainly made on red deer vestigial canines [7]. Personal ornaments also seem to be more common in later that in early UP layers, suggesting an increase of its importance from early to more recent UP phases. Still, such a scenario could be biased because in Dzudzuana for example, only a small part of the potentially occupied site surface was excavated [13]. Moreover, in Satsurblia the archaeological research is still ongoing, and thus we lack a complete picture of the site occupations precluding a definite comparison between early and later UP occupations [17].

The presence, at least in Satsurblia, of red deer teeth pendants from the early phases of the UP occupation on site appear to share behaviours in the symbolic sphere of the Caucasus UP societies with their counterpart groups in the Levant [142, 143].

The significance of red deer within the symbolic world of the Caucasian UP inhabitants of Dzudzuana and Satsurblia, in spite of their relative low abundance in the faunal remains when compared with other mammals (i.e., Capra caucasica, Bos/Bison) as in Mezmaiskaya, supports contacts and exchanges between North and South Caucasus in the late Pleistocene, already observed through the characteristics of the lithic assemblages. Also, identical techniques–mainly scraping, bifacial gouging and rotation–were employed by both, the Northern and Southern Caucasian UP groups to produce personal ornaments, although these techniques have been demonstrated to show certain flexibility, also observed in the early UP from other Eurasian areas. The technical choices and, especially, the taxonomic selection to produce the personal ornaments could imply the existence of cultural bonds between the Caucasian, Levantine and European hunter-gatherer groups at the early stages of the UP, considering the wide spread of this behavior all over Eurasia.

The data we present herein adds a significant aspect to the symbolic sphere of the Caucasus Palaeolithic societies, furthering our knowledge of late Pleistocene humans in the region. Recent studies have highlighted the importance of ornaments, be they perforated shells, or bone and teeth beads/pendants [48, 144–147]. It is now a given that understanding technological behaviors reflected in bone-implements and ornaments manufacture can greatly contribute to the study of the emergence and diffusion of Eurasian UP techno-cultural entities as well as their intra-actions and interactions, locally and globally [51, 52, 72, 148]. In the Caucasus, although the EUP lithic assemblages resemble more the contemporaneous Levantine Ahmarian than the European Early Aurignacian and the ‘Classic’ Levantine Aurignacian [7, 13, 14], the manufacture of the pendants and the taxa selected is closer to those from the EUP of the Levant. Bone implements are well represented in most of the Northern and Southern sites of the Caucasus. They will also further contribute, together with personal ornaments, to the refining of our knowledge as regards the techno-typological and conceptual behaviours of the last hunter-gatherers of the region, likely more complex than expected, and will highlight regional and trans-regional population and/or ideas movements.