Isotopic Insights from Prehistoric Feasting

"Our research highlights the strong parallels between the intense concentrations of activity associated with feasting event(s) at various henges and enclosures in southern Britain around 2500 BC, including Durrington Walls, Mount Pleasant and West Kennet palisaded enclosures, and at Newgrange. While there are clear similarities and differences in the character of the monuments at these places, contemporaneous largescale seasonal gatherings at midwinter for monument building and feasting occurred at each. At Newgrange and Durrington Walls, at least, we can now say that the feasting was focused on pigs that had been specially fattened on mast in advance. In combination, this suggests that these places may have been strongly interconnected through highly fluid and intersecting webs of contact at this time, thereby resulting in shared practices and worldviews."

Guiry E., Beglane F., Carlin N., Orton D., Teeter M., Szpak P.(2025). Pigs, pannage, and the solstice: isotopic insights from prehistoric feasting at Newgrange. Proceedings of the Prehistoric Society, 1–21, https://doi.org/10.1017/ppr.2025.10063

A fascinating study which will lead to reinterpretation of much Neolithic feasting data. The isotopic evidence from fattening on mast is important.

On a quick read through I am a little concerned that it seems that the peak of pig slaughtering was more likely to be November rather than at the Solstice for their conclusions. This is based on May farrowing which is at the end of the seasonality of Wild Boar and pigs raised naturally. 

Neolithic Trackway Mats Theory: A Novel Addition to Megalith Transport Proposals

AI was challenged to propose a novel addition to the debate on how Neolithic megaliths were moved. The result is the Neolithic Trackway Mats Theory, a practical and original idea drawing from modern engineering and known Neolithic technology. (If this has been proposed before apologies for failing to identify a source.)

Theory Overview

The core idea involves using Neolithic ground mats—constructed from bundled or woven branches, reeds, or similar biodegradable materials—to create temporary trackways across difficult or soft terrain. These mats would be laid ahead of the megalith to provide a firm base, reducing resistance when moving massive stones. They could be moved and reused, similar to modern site trackways used for heavy vehicles on soft ground. This method would be particularly effective for crossing bogs, marshes, or waterlogged soils, common in many British Neolithic landscapes.

Modern Parallels

Portable ground protection mats are widely used today. Heavy machinery, cranes, and even tanks move across soft or fragile ground by placing mats under their tracks or wheels. These mats distribute weight, prevent sinking, and can be repositioned as needed. The concept translates easily to Neolithic conditions, given the resources and technology available at the time. For example, see modern archaeology compounds.

Neolithic Implementation

Neolithic communities had the skills to construct trackway mats from reeds, branches, bracken, hides or woven timber. Unlike the permanent brushwood foundations of the Sweet Track near Glastonbury, this theory proposes temporary, moveable mats. Preconstructed mats could be placed to form a temporary trackway, lifted, and moved forward as stone transport progressed. These mats would prevent rollers or sledges from sinking into the soil, reduce friction, and support immense weights on weak surfaces, particularly in soft valley floors, ancient bogs, or glacial till.

Trackway mats would make it easier for people—and possibly draught animals—to move heavy stones across rough or soft terrain. By spreading the load over a wider surface area, mats prevent sinking into mud or ruts, which would otherwise cause delays. The textured surfaces of the mats also improve traction, reducing slipping risks while pulling or pushing. Mats effectively transform uneven or boggy terrain into a temporary roadway, enabling more efficient transport with less effort.

Integration with Timber Rail Systems

The trackway mats theory complements existing timber rail systems proposed for Neolithic stone transport. Mats could be placed beneath and around timber rails to stabilise them and ensure they remain level on uneven or soft ground. This creates a consistent surface, reducing the likelihood of rails shifting or sinking. Mats also simplify the process of laying rails, preventing them from sinking during placement, and facilitate sledge movement by minimising friction. Workers could alternate between extending mats and rails, enabling rapid progress across varied terrain.

Potential Advantages

• Reduces friction and prevents sinking of sledges or rollers
• Makes previously impassable terrain navigable
• Requires only modest additional labour and materials
• Leaves few archaeologically visible traces, explaining the lack of direct evidence
• Provides continuity with later timber trackways

Conclusion

The Neolithic trackway mats theory offers a practical, resource-conscious solution to the challenge of moving megaliths across Britain's varied landscapes. Drawing on modern engineering and archaeological precedent, the simplicity and adaptability of mats could have made them indispensable in Neolithic construction.

Appendix: Timber Rails or Slipways

Several studies have explored timber slipways (or rails) for megalith transport. Below is a summary of key findings:

Key Research Findings

• Experimental archaeology: Full-scale experiments showed a 40-ton block could be moved on an oak sledge over a greased timber-rail slipway, requiring around 130 people on a 1:20 slope.
• Contrasted with roller theories: Slipways are argued to be more efficient and better supported by ethnographic parallels than free-rolling logs.
• Lubrication: Pig fat, tallow, and other greases were likely used to reduce friction on wooden rails.
• Ethnographic reinterpretations: Images from Nias and Sumba, once thought to show rollers, are now interpreted by some as evidence for static timber slipways.

References

• Richards, J and Whitby, M, ‘The engineering of Stonehenge’, in Science and Stonehenge, ed B Cunliffe and C Renfrew, Proceedings of the British Academy 92 (Oxford, 1997), 231–56. Demonstrates the use of an oak sledge on a greased timber-rail slipway. Link
• R. H. G. Parry (2000); Megalith mechanics. Proceedings of the Institution of Civil Engineers - Civil Engineering, 138(4): 183–192. Discusses sleds on lubricated timber rails. Link
• Harris, Barney. (2018a). Roll Me a Great Stone: A Brief Historiography of Megalithic Construction and the Genesis of the Roller Hypothesis. Oxford Journal of Archaeology, 37: 267–281. Link
• Harris, Barney. (2018b) Moving megaliths: time to park the rollers. British Archaeology, Dec 1, 2018. Reinterprets ethnographic photos as evidence of slipways. Link
• Shillito, L.-M. (2019) ‘Building Stonehenge? An alternative interpretation of lipid residues in Neolithic Grooved Ware from Durrington Walls’, Antiquity, 93(370): 1052–1060. Suggests pig fat was used to grease sledges and rails. Link

Stone Shifting Papers

Two open access papers from Barney Harris - essential downloads for anyone interested in neolithic megalith transport. 

Roll Me a Great Stone: A Brief Historiography of Megalithic Construction and the Genesis of the Roller Hypothesis

Harris, B. (2018) Roll Me a Great Stone: A Brief Historiography of Megalithic Construction and the Genesis of the Roller Hypothesis. Oxford Journal of Archaeology, 37: 267–281. https://doi.org/10.1111/ojoa.12142.

Summary

The idea that prehistoric, megalith-building communities used cylindrical, wooden rollers to transport enormous stones – the ‘roller hypothesis’ – is ubiquitous within archaeological literature and public discourse on megalithic architecture. The likelihood that such devices were actually used to transport megaliths during prehistory remains highly questionable, yet the roller hypothesis has now dominated discussions of the subject for some 400 years. At its heart lies the assertion that fewer people were needed to transport large stones with rollers than without them. A review of experimental and ethnographic studies of megalith transport casts doubt on this central claim and suggests that simpler, better-attested and more reliable methods were probably used.

Landscapes of labour: a quantitative study of earth-moving and stone-shifting in prehistoric northern Wessex

Harris, Barney; (2020) Landscapes of labour: a quantitative study of earth-moving and stone-shifting in prehistoric northern Wessex. Doctoral thesis (Ph.D), UCL (University College London). 

whole_thesis_correction_oct2019.pdf - Accepted Version  Download (286MB)

Abstract 

The study explores the construction of Neolithic and Bronze Age monuments in the region of northern Wessex in terms of the labour invested in their creation. A historiography of ‘megalithic construction studies’ is initially presented, along with an account of experimental studies evaluating different approaches to the material problems likely experienced by prehistoric monument builders. A summary of the various forms of prehistoric structure found throughout northern Wessex is then provided, along with any archaeological observations relating to their construction.

Ramson Cliff Boulder 2025

The Ramson Cliff Boulder

Elevation: 80 m

OS Map: SS 43605 40758

Lat Long: 51.14466, -4.23723

https://w3w.co/overlaps.shuffle.narrate   

I visited Baggy Point today locate the present position and condition of the Ramson Cliff Erratic, it is quite overgrown and about 1.5m north of the cliff path. Compared to the c1974 photo it is now covered with lichen and moss, and surrounded by gorse. 

Click to embiggen

The erosion on the cliff path reveals the underlying bedrock, very rough and friable, not the smooth form of a stoss slope.

Further along Baggy Point there are dummy pillboxes from the D-Day training, well worth a visit as well.

The absence of Erratics in southern Britain - the latest research

Colin A. Whiteman, Periglacial landforms and landscape development in southern England,

Proceedings of the Geologists' Association, Volume 136, Issues 1–2, 2025, 101059, ISSN 0016-7878,

https://doi.org/10.1016/j.pgeola.2024.04.006.

(https://www.sciencedirect.com/science/article/pii/S0016787824000178)

Abstract: The south-central and south-east England Geological Conservation Review region is unique in Britain in lying completely outside the margins of Quaternary ice sheets. In view of this, the area has been described as a ‘relict periglacial landscape’. This implies that the region has evolved its current form substantially under the influence of seasonal and/or perennial frost. In fact, modern research has demonstrated that permafrost, either continuous or discontinuous, likely existed across probably the whole of the region at different times during the Quaternary...

"There have been a few speculative claims of glaciation occurring within this GCR region (e.g., Martin, 1920; Kellaway et al., 1975), but they have received negligible, if any, support. Far-travelled erratics are conspicuously absent from the region, except on the West Sussex coastal plain around Selsey, and these have been attributed to ice rafting on the basis of striations scored across underlying Cenozoic clays. If there ever were local glaciers within south-central and southeast England, it is unlikely that they would have deposited easily-recognisable erratics. Furthermore, no convincing glacial landforms have been described, and computer modelling (Hubbard et al., 2009; Clark et al., 2018) appears to support the absence of glaciation from this region. Thus it can safely be assumed that, uniquely in Britain, the Quaternary GCR area covering south-central and south-eastern England remained beyond the outermost margins of all Quaternary ice sheets." 

Stonehenge’s Bluestones: Putting Human vs. Glacial Transport to the AIC Test

1. Human Transport Theory — Neolithic builders quarried and deliberately hauled the stones from Preseli to Stonehenge.

2. Glacial Transport Theory — Glaciers during a past ice age moved the stones part or all of the way, leaving them for humans to collect.

The debate is often framed qualitatively, but here ChatGPT put the competing hypotheses into a statistical model comparison using the Akaike Information Criterion (AIC). This approach allows us to quantify which theory better explains the total body of evidence — and to measure the strength of that preference.

ChatGPT chose and researched the criteria without my input,to avoid any accusations I have biased the test. For instance I would have included the recent Bevins et al Newall Boulder paper which it doesn't appear to do so. The prompt used was: "Using Akaike Information Criterion (AIC) evaluate the Human vs the Glacial Transport Theories for the bluestones at Stonehenge" and then a further prompt to "dig deep and run a realistic calculation". The text and analysis is by ChatGPT.

---

AIC in Brief

AIC evaluates models by balancing:

• Goodness of fit (how well the model explains the data)

• Parsimony (penalising models with more free parameters)

For a model $M$:

$$\text{AIC} = 2k - 2 \ln(\hat{L})$$

Where:

• $k$= number of estimated parameters

• $\hat{L}$= maximum likelihood of the model given the data

Lower AIC indicates the better balance of fit and simplicity. A ΔAIC greater than 6 is typically considered strong evidence for the lower-AIC model.

---

Building the Models

ChatGPT treated each transport theory as a predictive model:

Human Transport predicts:

• Specific source outcrops match the bluestones.

• Evidence of quarrying at Preseli.

• No glacial erratic trail into Salisbury Plain.

• Dates of extraction and placement coincide with human activity.

Glacial Transport predicts:

• Erratics from Preseli present in southern England.

• Geological signs of glaciation in Wessex.

• Stones represent a random glacial mix.

• No need for extensive Neolithic transport infrastructure.

---

The Dataset

ChatGPT compiled 10 published, peer-reviewed observations from the last two decades. Examples:

• Geochemical fingerprinting of rhyolitic debitage at Stonehenge ties it to Craig Rhos-y-felin, and dolerite matches Carn Goedog — two very specific Preseli sources.

• Quarry-like features with Neolithic radiocarbon dates have been reported (though contested).

• Surveys of ~50,000 Avon terrace pebbles found no extra-basinal erratics.

• The last British–Irish Ice Sheet never reached Salisbury Plain; no local glacial deposits are known.

• The “Newall boulder” from 1924 excavations matches Preseli lithology and is argued not to be a glacial erratic.

• Strontium isotopes of cremated remains at Stonehenge reveal individuals from the Preseli region.

• Counter-evidence: some geologists interpret at least one Stonehenge boulder as glacial, and others argue quarry “features” may be natural.

---

Assigning Likelihoods

For each observation, ChatGPT estimated the likelihood $P(D|M)$ that such evidence would be seen if the model were true. For example:

Observation	P(Human)	P(Glacial)
No erratic trail to Stonehenge	0.85	0.05
Quarry-like features at Preseli	0.80	0.30
One boulder possibly glacial	0.35	0.65

Multiplying the probabilities across all ten observations gives the model likelihood. With $k=0$ (no parameters estimated from the data), AIC reduces to $-2\ln(L)$.

ID	Observation	P(Human)	P(Glacial)	ln P(Human)	ln P(Glacial)
E1	Rhyolitic debitage at Stonehenge matches Craig Rhos-y-felin (specific Preseli outcrop).	0.9	0.3	-0.10536	-1.20397
E2	Spotted dolerite matches Carn Goedog; quarry-like features & dates ~3350–3000 BC reported.	0.8	0.3	-0.22314	-1.20397
E3	Avon terrace survey (~50k pebbles) found no extra-basinal erratics near Stonehenge.	0.85	0.05	-0.16252	-2.99573
E4	No glacial deposits on Salisbury Plain; Devensian limit far away; Anglian evidence absent locally.	0.8	0.2	-0.22314	-1.60944
E5	The 'Newall boulder' from the 1924 excavation geochemically tied to Craig Rhos-y-felin; argued non-erratic.	0.75	0.25	-0.28768	-1.38629
E6	Strontium isotopes of cremations show some individuals from West Wales (Preseli region).	0.6	0.4	-0.51083	-0.91629
E7	Preseli lithologies concentrated at Stonehenge; no 'erratic train' between Preseli and Wessex.	0.85	0.1	-0.16252	-2.30259
E8	Bluestones include multiple distinct Preseli lithologies traceable to specific sources (non-random mix).	0.8	0.4	-0.22314	-0.91629
E9	Peer-reviewed critique argues quarry 'features' may be natural (reduces strength of quarry claim).	0.4	0.6	-0.91629	-0.51083
E10	Peer-reviewed paper promotes glacial-transport reading of at least one Stonehenge boulder.	0.35	0.65	-1.04982	-0.43078

---

Results

Model	ln L	AIC	ΔAIC	Akaike Weight
Human Transport	−3.86	7.73	0.00	0.9999
Glacial Transport	−13.48	26.95	19.22	0.0001

Interpretation:
ΔAIC ≈ 19 is far beyond the usual “strong evidence” threshold. The Human Transport model overwhelmingly outperforms the Glacial Transport model given the current dataset. The Akaike weight (~99.99%) can be read as the probability that the Human model would be selected as the better among these two, if the analysis were repeated with similar data.

---

Robustness Check

ChatGPT ran a conservative sensitivity test, reducing the likelihoods for Human-leaning evidence and increasing those for Glacial-leaning evidence. Even then:

• Human: AIC = 11.17, weight = 0.983

• Glacial: AIC = 19.25, weight = 0.017

The ranking stayed the same, and the Human model retained decisive support.

---

Why the Human Model Wins

The statistical edge comes from multiple, converging lines of evidence:

• Tight geological matches to specific Preseli outcrops.

• Lack of supporting glacial deposits or erratic trails in the region.

• Archaeological connections between Preseli and Salisbury Plain during the relevant time frame.

While some uncertainties remain — especially regarding the nature of “quarry” features — the overall pattern fits human agency much more closely than glacial happenstance.

---

Conclusion

Applying AIC reframes the bluestone transport debate from a narrative clash to a quantitative test. On the present evidence, the Human Transport theory is not just slightly better — it is orders of magnitude more likely than the Glacial Transport theory to explain the Stonehenge bluestones.

(Grok produced similar numbers when asked the same question and was given the same freedom to research and score)

Rerunning the test with the fully referenced evidence table from https://www.sarsen.org/2025/08/evidence-for-glacial-transport-theory.html gave this:  

Results:

Model	ln L	AIC (k=0)	ΔAIC	Akaike weight
Human transport	−1.625	3.25	0.00	~1.0000
Glacial transport	−18.971	37.94	34.69	~0.00000003

Interpretation:
With ΔAIC ≈ 34.7, the Human Transport theory is overwhelmingly preferred over the Glacial Transport theory on this dataset — the Akaike weight is essentially 100% in favour of human transport. 

The probability (relative likelihood) that the higher-AIC model is the best, compared to the lowest AIC model, is calculated as: exp(−0.5×ΔAIC)exp(−0.5×ΔAIC)

For ΔAIC = 34.7: exp(−0.5×34.7)=exp(−17.35)≈2.9×10−8exp(−0.5×34.7)=exp(−17.35)≈2.9×10−8

This is so close to zero that, statistically, you can be extremely certain the higher AIC model is not the best.

The Stonehenge Glacial Transport Theory

• 
  
  

• The full history, or obituary, of the theory for posterity.
  
  

• https://www.researchgate.net/publication/394479847_The_Stonehenge_Glacial_Transport_Theory

Atkinson's Bluestone Photographs

Parchmarks at Stonehenge 2025

Historic England have made an album of aerial photos of Stonehenge following the dry weather showing the parchmarks available. Taken on 11 July 2025 by James O Davies

https://historicengland.org.uk/images-books/photos/job/2K/32639

Much to examine, and to compare with the original parchmark paper.

Banton, S. et al. (2014) ‘Parchmarks at Stonehenge, July 2013’, Antiquity, 88(341), pp. 733–739. doi:10.1017/S0003598X00050651.

Rage, Rage Against The Dying Of A Theory

In the interest of fairness I should note that Dr John has responded to the death notice for the Glacial Transport theory.  To my eyes it is a chaotic blend of ad hominems, baseless self-cited claims, and a nonsequitous conflation of quarrying with glacial transport, despite the latter’s independence from the former. http://dx.doi.org/10.13140/RG.2.2.36446.96323

To set the record straight, Dr John accuses me of asking Researchgate to tweak my papers typeface to mimic a journal—calling it a ‘cheap stunt.’ I didn’t. Whatever he perceives is mere paranoid pareidolia; I use Word’s default fonts, and Researchgate hosts PDFs as submitted, as he’s well aware.

Blow, ye scholars, and rend your learned tomes! Ye Daw and Bevins, with your quills so sharp, Spout your refutations, drown my boulder’s truth! Rumble, ye journals, with your peer-reviewed scorn! Spit, ye XRF machines, and SEM-EDS lies! I am a king of ice, a geomorph’s sage, Whose glacial theory ye dare call dead and cold!
Here I stand, with map of Preseli’s frost, The Newall Boulder’s facets, my crown of proof! No striations, say ye? Mere weathering’s tale? I laugh at thy naivety, ye lumpers blind! Forty-six rock types, by my troth, I count, Not thy scant twelve—human hands ne’er moved these stones! Ice did the labour, o’er Salisbury’s plain it swept, Yet ye, with quarrying dreams, deny my reign!
Let the storm of thy papers crack and fall, Thy Rhosyfelin quarry, a phantom’s jest! No wedges nor rails, but nature’s own art, And I, old John, shall prove it with my fist! Parker Pearson’s ghosts, abandon thy claims, Waun Mawn’s erratics mock thy dismantled throne! I’ll rant ‘gainst this tide, though the world turn deaf, For glacial glory shall rise, or I’ll curse the sod!

 

Evidence for the Glacial Transport Theory of Stonehenge

The Glacial Transport Theory posits that the bluestones (and potentially other megaliths) at Stonehenge were primarily moved from their Welsh origins to Salisbury Plain by glacial action during the Pleistocene, rather than through human effort, implying they were collected locally near Stonehenge as erratics rather than quarried, and/or collected, in Wales and transported. 

Below is a comprehensive list of key evidence types that could prove or disprove this theory (or render it likely/unlikely), based on geological, archaeological, and glaciological principles. For each, we indicate whether it supports or refutes the theory, and annotate whether such evidence has been found, with details drawn from scientific analyses.

Evidence Table

Evidence Type	Supports or Refutes Theory	Has It Been Found?	Details and Sources
Presence of bluestone glacial erratics (boulders of matching lithology) scattered across Salisbury Plain, outside the immediate Stonehenge environs	Supports (would indicate widespread glacial deposition, allowing humans to collect them locally)	No	No bluestone erratics have been identified on Salisbury Plain beyond Stonehenge itself, despite extensive surveys; this absence contradicts expected glacial dispersal patterns
Evidence of glacial deposits, sediments, or landforms (e.g., moraines, till) on or near Salisbury Plain	Supports (would confirm ice sheets reached the area, enabling transport)	No	No glacigenic sediments, depositional landforms, or glacio-tectonic structures have been found on Salisbury Plain or adjacent areas east of north Somerset, inconsistent with glacial incursion. River gravels in nearby valleys (e.g., Wylye, Nadder, Avon) also lack glacially derived materials
Glacial striations, faceting, or subglacial microwear on bluestones (e.g., scratches, gouges from ice pressure)	Supports (diagnostic of glacial modification during transport)	Disputed, but predominantly no	Some proponents claim faint striations on artefacts like the Newall Boulder indicate subglacial features, but recent petrographic, SEM-EDS, and XRF analyses show these are likely natural slickensides or fault-related, not glacial; no definitive glacial striations found on bluestones overall
Geological or palaeoclimatic evidence that ice sheets extended to Salisbury Plain during relevant Pleistocene periods (e.g., Anglian or Wolstonian glaciations)	Supports (establishes feasibility of ice reaching the site)	No	Ice flow models and stratigraphy show glaciers did not extend east of the Somerset lowlands or south of the Vale of Moreton; topographic barriers (e.g., Mendips) and lack of evidence in southern England contradict this
An erratic dispersal train (trail of bluestone fragments) between Preseli Hills and Salisbury Plain	Supports (consistent with glacial dilution and deposition patterns)	No	No continuous train of erratics exists across southern England; dispersal fans (e.g., spotted dolerites) stop short and do not align with Stonehenge. Isolated finds (e.g., Gower coast boulder) are not on the direct path
Absence of Neolithic quarrying sites or extraction evidence in the Preseli Hills source areas	Supports (suggests stones were natural erratics, not human-quarried)	No	Quarries identified at Carn Goedog (spotted dolerite source) and Craig Rhos-y-felin (rhyolite source), with platforms, trackways, and tools indicating extraction
Evidence of quarrying tools, methods, or debitage (waste flakes) at Welsh sites matching Stonehenge stones	Refutes (indicates human extraction and transport from origin)	Yes	Stone wedges, hammer stones, loading platforms, and in-situ tools found at quarries; Newall Boulder identified as rhyolite debitage from a broken monolith (e.g., Stone 32d), showing human shaping
Dating of quarrying activity aligning with Stonehenge's construction phases (ca. 3000–2500 BC)	Refutes (links extraction to human timeline, not ancient glaciation)	Yes	Charcoal and platform dates from quarries yield ca. 3000 BC, matching Stonehenge's bluestone phase; chlorine-36 dating on a bluestone suggests exposure ca. 14,000 years BP, consistent with post-glacial human quarrying
Geochemical and petrographic matching of Stonehenge bluestones to specific Welsh quarries (without glacial intermediaries)	Refutes (supports direct human sourcing from known sites)	Yes	Bluestones match Preseli outcrops (e.g., Carn Goedog for dolerite, Craig Rhos-y-felin for rhyolite); Newall Boulder provenance confirmed as Craig Rhos-y-felin via XRF and SEM-EDS
Evidence of human transport routes or capabilities (e.g., parallels in other Neolithic sites)	Refutes (demonstrates feasibility of human movement over 200+ km)	Yes	Archaeological parallels exist for long-distance megalith transport; proposed routes via Bristol Channel or overland, with evidence like Waun Mawn circle suggesting disassembly and relocation

Conclusion

This evidence collectively makes the Glacial Transport Theory unlikely, as the preponderance (e.g., quarrying sites, absence of erratics/deposits) supports human transport. Proponents argue glaciers could move such boulders based on general capabilities, but lack site-specific proof. Recent studies have further refuted key claims, such as the Newall Boulder's glacial origin 

References

1. 1. Kellaway, G. A. (1971). Glaciation and the stones of Stonehenge. Nature, 233(5314), 30–35. https://doi.org/10.1038/233030a0
   2. Thorpe, R.S. et al. (1991) ‘The Geological Sources and Transport of the Bluestones of Stonehenge, Wiltshire, UK’, Proceedings of the Prehistoric Society, 57(2), pp. 103–157. http://dx.doi.org/10.1017/S0079497X00004527 
   3. Williams-Thorpe, O., Jones, M. C., Potts, P. J., & Webb, P. C. (2006). Preseli dolerite bluestones: axe-heads, Stonehenge monoliths, and outcrop sources. Oxford Journal of Archaeology, 25(1), 29–46. archaeologydataservice.ac.uk
   4. Green, C. P. (1997). Stonehenge: Geology and prehistory. Proceedings of the Geologists’ Association, 108(1), 1–10. https://doi.org/10.1016/S0016-7878(97)80001-6.
   5. Clark, C.D., Hughes, A.L., Greenwood, S.L. et al.  (2012) Pattern and timing of retreat of the last British-Irish Ice Sheet. Quaternary Science Reviews, 44. 112 - 146. ISSN 1873-457X https://doi.org/10.1016/j.quascirev.2010.07.019
   6. Gibson, S.M. and Gibbard, P.L. (2024), Late Middle Pleistocene Wolstonian Stage (MIS 6) glaciation in lowland Britain and its North Sea regional equivalents – a review. Boreas, 53: 543-561. https://doi.org/10.1111/bor.12674
   7. Gibbard, P.L. and Clark, C.D. (2011) ‘Pleistocene Glaciation Limits in Great Britain’, in Ehlers, J., Gibbard, P.L. and Hughes, P.D. (eds.) Developments in Quaternary Sciences. Volume 15. Amsterdam: Elsevier, pp. 75–93. ISBN 9780444534477 https://doi.org/10.1016/B978-0-444-53447-7.00007-6.
   8. Ixer, R. A., & Turner, P. (2004). A detailed re-examination of the petrography of the Altar Stone. Wilts Archaeological Magazine, 97, 1–9.
   9. Bevins, R. E., et al. (2025). The enigmatic ‘Newall boulder’ excavated at Stonehenge in 1924: New data and correcting the record. Journal of Archaeological Science: Reports, 66, 105303. https://doi.org/10.1016/j.jasrep.2025.105303.
   10. Bowen, D. Q. (1999). A revised correlation of Quaternary deposits in the British Isles. Geological Society, London, Special Report, 23.
   11. John, B. S. (2008). The Bluestone Enigma. Greencroft Books.
   12. Pearson, M.P. et al.(2015) ‘Craig Rhos-y-felin: a Welsh bluestone megalith quarry for Stonehenge’, Antiquity, 89(348), pp. 1331–1352. https://doi.org/10.15184/aqy.2015.177.
   13. Pearson, M.P. et al. (2019) ‘Megalith quarries for Stonehenge’s bluestones’, Antiquity, 93(367), pp. 45–62. https://doi.org/10.15184/aqy.2018.111.
   14. Ixer, R.A., Bevins, R.E., 2017. The bluestones of Stonehenge. Geology Today 33, 180-184.
   15. Ixer, R.A., Turner, P., Molyneux, S., Bevins, R.E., 2017. The petrography, geological age and distribution of the Lower Palaeozoic Sandstone debitage from the Stonehenge Landscape. Wiltshire Archaeology and Natural History Magazine 110, 1-16.
   16. Pearson, M.P. et al. (2021) ‘The original Stonehenge? A dismantled stone circle in the Preseli Hills of west Wales’, Antiquity, 95(379), pp. 85–103. https://doi.org/10.15184/aqy.2020.239.
   17. Bevins, R.E., Pearce, N.J.G., Ixer, R.A., Scourse, J.D., Daw, T., Parker Pearson, M., Pitts, M., Field, D., Pirrie, D., Saunders, I., Power, M., 2025. The enigmatic ‘Newall boulder’ excavated at Stonehenge in 1924: New data and correcting the record. Journal of Archaeological Science: Reports 66 https://doi.org/10.1016/j.jasrep.2025.105303
   18. Bevins, R. E., et al. (2012). Provenancing the rhyolitic and dacitic components of the Stonehenge bluestones. Journal of Archaeological Science, 39(4), 1005–1019. https://doi.org/10.1016/j.jas.2011.11.020.
   19. Ixer, R.A. & Bevins, R.E. (2017). The bluestones of Stonehenge. Geology Today. 33. 180-184. https://doi.org/10.1111/gto.12198.
   20. Darvill, T. and Wainwright, G. (2009). Stonehenge excavations 2008. Antiquaries Journal, 89 (1), 1-19.
   21. Parker Pearson, M. (2021). Stonehenge: Exploring the greatest Stone Age mystery. Simon & Schuster.
   22. John, B. S. (2018). The Stonehenge bluestones. Greencroft Books.
   
   

A tale of two boulders

Comparative Analysis of the "Brian John Boulder" at Craig Rhos-y-felin and the "Newall Boulder" from Stonehenge: Implications for the Origins and Transport of the Bluestones
- a paper - DOI: 10.13140/RG.2.2.28445.01769

The shape and surface of a boulder tells its story. The "Brian John Boulder" (left) was found in-situ at Craig Rhos-y-felin, the "Newall Boulder" (right) at Stonehenge.

"The comparison between the “Brian John Boulder” at Craig Rhos-y-felin and the “Newall Boulder” from Stonehenge reveals that both exhibit distinctive bullet-like morphologies shaped by foliation, along with comparable surface abrasion and weathering features. These characteristics show no evidence of long-distance glacial transport and are more convincingly explained by in situ weathering at the source, followed by deliberate Neolithic extraction and movement. The combined geological and archaeological evidence strongly supports human agency in the sourcing and transport of Stonehenge’s bluestones. Crucially, if the Newall Boulder had been transported over 200 km by glacial action, it would not so closely resemble clasts still in place at Craig Rhos-y-felin."

The Brian John Boulder

The Brian John Boulder: Picture Dr Brian John

Other debris and bullet shaped clasts: Picture: Dr Brian John

 Dr Brian John brings to our attention a bullet shaped clast of Rhyolite in the debris at Craig Rhosyfelin.

At Craig Rhosyfelin (also spelt Rhos-y-felin), a rocky outcrop of Ordovician rhyolite in north Pembrokeshire, Wales, the geological context reveals a site shaped predominantly by local glacial, periglacial, and fluvioglacial actions during the Late Devensian (last glacial episode, circa 20,000–11,000 years ago). The outcrop lies within a meltwater channel incised by glacial activity, where ice sheets from the Irish Sea Glacier overrode the area, causing direct abrasion and plucking without necessitating long-distance clast movement. Features previously interpreted as indicators of far-field glacial transport—such as the bullet shape, abraded surfaces, and weathering crusts—are re-evaluated here as products of localised, in-place modification. This aligns with geomorphological critiques that emphasise natural processes over anthropogenic quarrying or extensive ice entrainment, viewing the site's chaotic boulder litter as resulting from rockface disintegration, frost shattering, and short-range meltwater reworking.

1. Overall Shape and Morphology

The clast exhibits a bullet-like morphology: elongated (approximately 50–70 cm long), tapering to a pointed "nose" at one end while broadening to a blunter base at the other. Its contours follow the inherent foliation planes of the rhyolite, with subtle ridges and depressions aligned parallel to the rock's layered structure. In the image, it appears partially embedded in the sediment, amidst a scatter of similar fragments, suggesting detachment from the nearby outcrop.

This shape arises from natural fracturing along the rhyolite's prominent millimetre-scale foliation, which creates pillar-like forms prone to breaking into tapered segments. At Craig Rhosyfelin, the outcrop's vertical joints and planar banding facilitate such breakage under periglacial conditions, where repeated freeze-thaw cycles wedge apart weaknesses, producing rounded, bullet-like tips without any need for transport. Excavations have revealed numerous such detached "bullet stones" still at the site, confirming they result from in-place disintegration rather than ice flow dynamics. Local glacial overriding may have enhanced this by plucking blocks from the bedrock, but with minimal displacement—often mere metres—into adjacent meltwater channels. The asymmetry mimics streamlined forms but reflects differential weathering: exposed ends erode more via frost action, while basal connections to bedrock preserve blunter profiles.

2. Surface Characteristics and Abrasion Features

The surface is variably textured, featuring abraded facets (flat or curved planes), faint linear scratches, grooves aligned with the long axis, and minor pits or projections tied to the rock's lithology. The light grey-whitish tone in the image highlights these under ambient light, with potential microfeatures like arcuate indentations visible on closer inspection.

These abrasion traits stem from localised glacial and periglacial erosion at the outcrop itself. As Irish Sea Ice overrode the Preseli region, basal grinding against the bedrock—laden with embedded debris—created facets and striations without moving the clast far. Grooves and scratches likely formed from in situ pressure and shear along foliation planes, amplified by freeze-thaw expansion. Post-glacial exposure has added chemical etching and minor fluvial polishing from seasonal meltwater flows in the channel, but all within a few metres of origin. Such features are ubiquitous on frost-shattered rhyolite faces, where heavy abrasion occurs naturally from rockfall and colluvial movement, negating transport-related explanations.

3. Weathering Crust and Patina Development

A whitish weathering crust, up to several millimetres thick, coats the exposed surfaces unevenly, appearing chalky and flaking in places to reveal darker underlying rock. Distribution is patchy, thicker on upward-facing areas and thinner where sediment contact has offered protection.

This crust develops through prolonged post-glacial chemical weathering in place, via hydrolysis and oxidation in a humid, periglacial climate. Rhyolite's composition—rich in feldspar, chlorite, and quartz—promotes kaolinite rind formation, whitening exposed faces over millennia. At Craig Rhosyfelin, differential patina reflects partial burial in slope deposits after initial detachment, with no evidence of pre-weathering erasure by transport. Instead, it records static exposure since the Holocene, enhanced by local acidic soils and rainfall. Geomorphological studies attribute this to in situ periglacial action, where frost heaving and solifluction minimally shift clasts while accelerating surface degradation.

4. Clastic Fragments and Associated Debitage

Surrounding the clast are angular shards, rounded cobbles, and finer gravels of similar rhyolite, some with abraded edges or conchoidal fractures, forming an unsorted matrix in the fluvioglacial sediments.

These fragments result from localised rockface comminution via frost shattering and minor meltwater reworking. Pressure fractures occur along natural joints under ice load or thermal stress, with abrasion from mutual clast contact during short-range tumbling in seasonal streams. The chaotic litter represents accumulated rockfall and quarrying debris at the crag base, overlain by Holocene colluvium, without far-travelled erratics. Striated cobbles noted in exposures indicate in-place glacial polishing, but the assemblage's poor sorting points to periglacial slope processes rather than extensive transport.

5. Broader Contextual Erosion and Landscape Integration

The clast integrates into a site marked by jointed rhyolite crags, rockfall banks, and reddish sediments in a meltwater channel, with evidence of heavy abrasion on exposed surfaces.

The landscape records overriding by thin ice sheets, causing plucking and abrasion directly on the outcrop, followed by periglacial frost wedging that detaches pillar-like blocks. Fluvioglacial deposits suggest brief, high-energy meltwater episodes moving material only metres downslope. Disputed "engineering" features (e.g., platforms) may be reinterpreted as natural ledges from foliation-controlled erosion, with radiocarbon dates supporting intermittent occupation and quarrying.

Summary Table of Characteristics

Characteristic	Description in This Clast	How It Results from In Situ Events
Bullet Shape	Elongated taper along foliation, rounded tip	Frost shattering and plucking along natural planes; minimal displacement.
Abraded Facets & Scratches	Flat planes with grooves from pressure and shear	Local glacial overriding and periglacial grinding on bedrock.
Weathering Crust	Whitish rind on exposed faces, uneven	Post-glacial chemical alteration in place, protected by burial.
Clastic Fragments	Angular shards with fractures in unsorted matrix	Rockfall comminution and short-range meltwater abrasion.
Landscape Context	Chaotic litter in meltwater channel with jointed crags	Periglacial disintegration and fluvioglacial reworking locally.

In conclusion, the apparent glacial forms of this bullet-shaped clast are the result of in situ events at Craig Rhosyfelin. Overridden by ice during the Devensian, the outcrop underwent direct abrasion, plucking, and fracturing, with subsequent periglacial weathering and minor fluvioglacial adjustment detaching and modifying the clast within metres of its origin. This interpretation dismisses long-distance ice transport, viewing the features as natural outcomes of localised glacial and post-glacial processes.

Airmen's or Airman's?

 

Airmen's Cross near Stonehenge (That's not Stonehenge behind it, but Jeremy Deller's inflatable version.)

Stonehenge Education Projects - Archaeological Desk-Based Assessment

This is just one example of the confusion at the New Visitor Centre near Stonehenge. Airmen's or Airman's?

The cross itself commemorates two Airmen, so logically Airmen's. 

It's original inscription: "TO THE MEMORY/ OF/ CAPTAIN LORAINE/ AND STAFF-SERGEANT WILSON/ WHO WHILST FLYING ON DUTY MET WITH/ A FATAL ACCIDENT NEAR THIS SPOT/ ON JULY 5TH 1912./ ERECTED BY THEIR COMRADES"

The listed status description of the cross is quite clear - Airmen's   

The official War Memorial record of it - Airmen's Cross - but quotes an additional 1996 tablet inscription as "AIRMAN'S CROSS".

The road junction is more commonly Airman's Corner on maps, though it isn't noted as such until quite recently and Airmen's has been used, especially in professional reports.

It seems that the incorrect Airman's is winning as English Heritage increasingly use it. The singular form draws much of its staying power from Ordnance Survey maps and the 1996 dedicatory tablet added to the memorial itself, which explicitly labels it "AIRMAN'S CROSS." This acts as an authoritative anchor, influencing how English Heritage describes the monument in on-site signage, guidebooks, and social media posts, but the plural lingers in scholarly and commemorative circles, ensuring the confusion endures.

The Cunnington Family: Archaeological Lineage and Contributions (1754–1951)

I. William Cunnington I (1754–1810)

A pioneering Wiltshire antiquarian and early archaeologist. He undertook systematic excavations of Bronze Age barrows on Salisbury Plain in collaboration with Sir Richard Colt Hoare, including the famous Bush Barrow near Stonehenge. His methods laid groundwork for modern field archaeology.

Married Mary Meares in 1787.

Had four children: Mary (1788–1854), Elizabeth (1789–1866), Anne (1790–1873), and Thomas (d. 1815). Only Elizabeth continued the archaeological legacy through her descendants.

II. Elizabeth Cunnington (1789–1866)

Daughter of William I. Married her cousin William Cunnington II (1785–1846), a draper and wool merchant with no known archaeological activity. The marriage united two branches of the Cunnington family and produced several children who advanced the family's antiquarian pursuits.

III. William Cunnington III (1813–1906)

Son of Elizabeth and William II. A geologist and antiquarian, he founded the Wiltshire Archaeological and Natural History Society (WANHS) in 1853. Known for his geological collections and publications, he described fragments excavated at Stonehenge in 1881, notably in Stonehenge Notes: The Fragments (1884).

Known professionally as William Cunnington FGS of Clapham.

Played a crucial role in classifying and preserving artefacts related to Neolithic Wiltshire. Married Jane Elliott in 1844; their children are not well-documented in archaeological contexts but continued family lines in Devizes.

IV. Henry Cunnington (1820–1887)

Son of Elizabeth and William II; brother of William III. A wine merchant by profession in Devizes, but definitively credited as the field excavator (“Mr H. Cunnington”) at Stonehenge in 1880–1881, responsible for recovering bluestone and rhyolite fragments from buried stone stumps such as 32c.

These finds were later analysed and published by his brother William III.

Married Lydia Mary Buckland in 1849. Had 12 children, including Henry Alfred (1850–1879), Herbert James (1851–1915), Cecil William (1855–1934), Joseph Grace Smith (1859–?), Edward Benjamin Howard (1861–1950), and several daughters who supported family endeavours.

V. Benjamin Howard “Ben” Cunnington (1861–1950)

Son of Henry; great-grandson of William I. A prolific field archaeologist who took over his father's wine merchant business before dedicating himself to archaeology. Honorary curator of Devizes Museum (now Wiltshire Museum) for 60 years, and co-excavator of major prehistoric sites across Wiltshire, often with his wife Maud. Notable projects include:

• Woodhenge (1925–26)
• The Sanctuary, Avebury (rediscovered and excavated, 1930)
• All Cannings Cross, Knap Hill, Figsbury Ring, and more

Ben was the fourth generation of the family engaged in archaeological work. He and Maud donated sites and artefacts to the state and museum collections.

VI. Maud Edith Cunnington (née Pegge; 1869–1951)

Wife of Ben Cunnington (married 1889). An accomplished archaeologist in her own right, Maud directed excavations at West Kennet Long Barrow, Figsbury Ring, Woodhenge, and The Sanctuary. She authored guides to Avebury and Devizes Museum, was elected the first woman president of WANHS (1931), and received a CBE in 1948 for services to archaeology.

Though not biologically descended from William I, Maud was central to the family's archaeological impact in the 20th century.

VII. Edward Cunnington (d. 1918)

Only child of Ben and Maud. Killed in action during the First World War. No known involvement in archaeological work.

VIII. Robert Henry Cunnington (c.1878–1959)

Son of Henry Alfred Cunnington (and Annette Wright Leach); grandson of Henry Cunnington; great-great-grandson of William I. A family biographer and custodian of the legacy, though not a field archaeologist. He authored From Antiquary to Archaeologist: A Biography of William Cunnington (1754–1810) (published posthumously in 1975), a key source on the life of William I, including family tree details.

His work helped preserve and document the family's contributions.

A partial family tree:

Click to embiggen - from https://www.familysearch.org/en/tree/pedigree/portrait/M94V-WSG

The Parkers, Stephen and John, who were the labourers employed to excavate the barrows can be found at https://www.familysearch.org/en/tree/pedigree/portrait/M9S7-TSY

Footnotes (Expanded and Corrected Sources)

1. Colt Hoare, R. & Cunnington, W. (1812–1819). The Ancient History of Wiltshire. Longman.
2. WANHS archives, Devizes Museum; founding records, 1853.
3. Cunnington, W. (1884). Stonehenge Notes: The Fragments. Wiltshire Archaeological and Natural History Magazine, Vol. XXI.
4. Biodiversity Heritage Library (1884). p. 182. Retrieved from: https://www.biodiversitylibrary.org/page/44863738
5. Cunnington, B.H. (1929). The Sanctuary, Avebury. Devizes: WANHS.
6. WANHS memorials; Commonwealth War Graves Commission records.
7. The Times, Obituary of Maud Cunnington, 1951; British Honours List, 1948.
8. Cunnington, R.H. (1975). From Antiquary to Archaeologist: A Biography of William Cunnington (1754–1810). Oxford: British Archaeological Reports.

Correcting the Lithological Identification of Buried Bluestone Stumps 32d and 32e at Stonehenge

Bevins et al (2025) is mainly noted for its forensic examination of the Newall Boulder and its confirmation that Glacial Transport played no part in transporting the bluestones to Stonehenge. However there is another research item within it which may be overlooked.  

Excavation of cutting C45 in the east sector of the site. Professor Atkinson (kneeling by Bluestone stumps 32d and 32e) examines a find

Acknowledgement and Citation

This standalone research extraction is derived directly from the following source, which provides the primary data, analysis, and evidence discussed herein:

Bevins, R.E., Pearce, N.J.G., Ixer, R.A., Scourse, J., Daw, T., Parker Pearson, M., Pitts, M., Field, D., Pirrie, D., Saunders, I., Power, M., 2025. The enigmatic ‘Newall boulder’ excavated at Stonehenge in 1924: New data and correcting the record. Journal of Archaeological Science: Reports 66, 105303. https://doi.org/10.1016/j.jasrep.2025.105303.(https://www.sciencedirect.com/science/article/pii/S2352409X25003360)

All interpretations, evidence, and conclusions presented below are based on this paper, with specific references to its sections, figures, and supporting data. This updated version integrates historical context from prior publications by Bevins and Ixer (and co-authors), tracing the evolution of identifications for Stones 32d and 32e. These earlier works progressively linked rhyolitic debitage to potential parent monoliths, shifting focus from 32e (suggested in 2011) to 32d (confirmed in 2015 onward), culminating in the 2025 correction.

Introduction

The Stonehenge monument includes several buried stumps of bluestones, which are smaller megaliths distinct from the larger sarsen stones. Among these, the stumps designated as Stones 32c, 32d, and 32e—located in the bluestone circle between upright bluestones 32 and 33—have been subject to historical misidentification (Bevins et al., 2025, Section 4). Originally excavated by Richard John Copland Atkinson in 1954, these stumps were described in Atkinson's publications (1956, 1979) as follows:

• Stone 32c: altered volcanic ash,
• Stone 32d: spotted dolerite,
• Stone 32e: rhyolite.

This identification has been perpetuated in subsequent literature, including plans by Thorpe et al. (1991), Williams-Thorpe and Thorpe (1992), and Cleal et al. (1995), leading to ongoing confusion (Bevins et al., 2025, Section 4). Recent re-examination of photographic evidence from Atkinson's 1954 excavation, combined with petrographic analysis, indicates that the identifications of Stones 32d and 32e were reversed. This correction aligns with the petrographical characteristics of known bluestone lithologies and supports provenancing efforts linking certain bluestones to sources in north Pembrokeshire, Wales (Bevins et al., 2025, Sections 3 and 4).

Historical Identifications in Bevins and Ixer Publications

Research by Bevins and Ixer on Stonehenge bluestones has evolved over time, initially focusing on debitage (stone fragments) and later linking these to buried stumps. Early work introduced the 'rhyolite with fabric' lithology (now Rhyolite Group C) from Craig Rhos-y-felin (formerly Pont Saeson), but did not address specific stumps (Ixer and Bevins, 2010; Bevins et al., 2012). By 2011, they tentatively suggested Stone 32e as a potential parent monolith for rhyolitic debitage, noting: "There is one buried stump at Stonehenge (stone 32e) that they say could well be from Pont Saeson (to be confirmed)" (Ixer and Bevins, 2011, as summarized in secondary sources like Pitts, 2011). This was based on petrographic matches but remained provisional.

In 2015, as co-authors with Parker Pearson et al., Bevins and Ixer shifted focus to Stone 32d, identifying it macroscopically as foliated rhyolite despite Atkinson's dolerite classification: "On the basis of macroscopic appearance, Bevins and Ixer identify SH32d... as a ‘spotted dolerite’ bluestone, even though its appearance is most unlike spotted dolerite. Its dimensions... correspond closely with those of a recess at Craig Rhos-y-felin" (Parker Pearson et al., 2015). This marked the first explicit re-identification of 32d as rhyolite, with no further emphasis on 32e in this context.

Subsequent references in later works (e.g., Bevins et al., 2023a; Parker Pearson et al., 2022a) reinforce this, but the 2025 paper provides the definitive correction using archival photos.

Evidence for Re-identification

Atkinson's excavation (Section C45) exposed the three buried stumps immediately north of Stone 33. A previously unpublished photograph from Historic England's archives (image P50774), taken during the 1954 excavation, provides visual evidence of their morphologies (Bevins et al., 2025, Figure 5a). Analysis of this photograph reveals distinct features:

• Stone 32c (northernmost stump): This appears as a darker, rounded, domed stump with a parallel fabric or parting, indicating weathering. It matches Atkinson's description of altered volcanic ash (tuff). Petrographic examination confirms it as Andesite Group A (Ixer et al., 2022, 2023; Bevins et al., 2025, Section 4). Thin sections from a sample collected by Henry Cunnington in 1881 (Salisbury Museum accession 1983.20.46) corroborate this, showing a chlorite-rich volcanic tuff (Bevins et al., 2025, Section 4).
• Stone 32d (central stump): This stump exhibits a strong foliation, breaking into planar sheets on a centimetre scale, forming steps and small ledges. Visible light/dark banding parallels the foliation (Bevins et al., 2025, Figure 5b). These characteristics are inconsistent with spotted dolerite (a massive, non-foliated igneous rock) but identical to foliated rhyolite from Craig Rhos-y-felin in north Pembrokeshire (Rhyolite Group C; Bevins et al., 2025, Section 4). For comparison, in-situ exposures at Craig Rhos-y-felin show similar centimetre-scale foliation and fracturing (Pitts, 2022; Bevins et al., 2025, Figure 5c).
• Stone 32e (southernmost stump, closest to Stone 33): This is a massive, blocky stump with flattish facets, lacking foliation. It aligns with spotted dolerite, not rhyolite as Atkinson described. Its resistance to weathering (evident in the domed but robust shape) further supports a dolerite classification, possibly spotted (Bevins et al., 2025, Section 4).

The misidentification likely stems from an error in Atkinson's recording or transcription, as the rock types are visually and texturally distinct (Bevins et al., 2025, Section 4). Cleal et al. (1995) compounded the issue by labelling both 32d and 32e as "spotted dolerite" in cross-sections, while marking 32c as uncertain. Other publications, such as Chippindale (1987) and Johnson (2008), often refer to these stumps generically as "bluestones" without specifying lithologies, perpetuating ambiguity (Bevins et al., 2025, Section 4).

Current online resources, such as the Stones of Stonehenge website (accessed 2025), reflect the corrected identifications:

• Stone 32c: Volcanic Group A (now Andesite Group A),
• Stone 32d: Rhyolite Group A-C (now Rhyolite Group C),
• Stone 32e: Dolerite (possibly spotted).

This aligns with broader provenancing studies, where Rhyolite Group C debitage at Stonehenge matches Craig Rhos-y-felin petrographically and geochemically (Bevins et al., 2011, 2012, 2023a; Bevins et al., 2025, Sections 3 and 4).

Implications

Correcting the identifications of Stones 32d and 32e has significant implications for understanding Stonehenge's construction and the sourcing of its bluestones (Bevins et al., 2025, Sections 4 and 10). Stone 32d, as foliated rhyolite, likely represents the parent monolith for debitage fragments, including the Newall boulder (excavated nearby in 1924 by Lt-Col Hawley; Bevins et al., 2025, Sections 2 and 4). This supports human transport from Welsh sources rather than glacial deposition, as the limited lithological variety at Stonehenge suggests selective quarrying from discrete locations like Craig Rhos-y-felin (Bevins et al., 2025, Sections 7 and 10).

The reversal also resolves discrepancies in earlier literature challenging links between Stonehenge rhyolites and Welsh outcrops (e.g., John, 2024a; Bevins et al., 2025, Section 4). Future studies should prioritise direct sampling of these stumps where feasible, though non-invasive methods (e.g., portable XRF) could confirm the re-identification without disturbance (Bevins et al., 2025, Section 3.2).

Conclusions

Re-examination of Atkinson's 1954 excavation photograph and petrographic comparisons demonstrates that Stone 32d is foliated rhyolite (Rhyolite Group C) and Stone 32e is spotted dolerite, reversing their original identifications. Stone 32c remains correctly identified as altered volcanic ash (Andesite Group A) (Bevins et al., 2025, Section 4). This correction refines the bluestone assemblage inventory and strengthens provenancing ties to north Pembrokeshire, emphasising the need for critical review of historical records in archaeological geology (Bevins et al., 2025, Section 10).

References

• Bevins, R.E., Pearce, N.J.G., Ixer, R.A., Scourse, J., Daw, T., Parker Pearson, M., Pitts, M., Field, D., Pirrie, D., Saunders, I., Power, M., 2025. The enigmatic ‘Newall boulder’ excavated at Stonehenge in 1924: New data and correcting the record. Journal of Archaeological Science: Reports 66, 105303. https://doi.org/10.1016/j.jasrep.2025.105303.
• Atkinson, R.J.C., 1956. Stonehenge. Hamish Hamilton, London.
• Atkinson, R.J.C., 1979. Stonehenge. Penguin Books, Harmondsworth.
• Bevins, R.E., Pearce, N.J.G., Ixer, R.A., 2011. Stonehenge rhyolitic bluestone sources and the application of zircon chemistry as a new tool for provenancing rhyolitic lithics. Journal of Archaeological Science 38, 605-622.
• Bevins, R.E., Ixer, R.A., Webb, P.C., Watson, J.S., 2012. Provenancing the rhyolitic and dacitic components of the Stonehenge landscape bluestone lithology: new petrographical and geochemical evidence. Journal of Archaeological Science 39(4), 1005-1019.
• Bevins, R.E., Ixer, R.A., Pearce, N.J.G., Scourse, J., Daw, T., 2023a. Lithological description and provenancing of a collection of bluestones from excavations at Stonehenge by William Hawley in 1924 with implications for the human versus ice transport debate of the monument's bluestone megaliths. Geoarchaeology 38, 771-785.
• Chippindale, C., 1987. Stonehenge Complete. Thames and Hudson, London.
• Cleal, R., Walker, K.E., Montague, R., 1995. Stonehenge in its landscape: twentieth-century excavations. Archaeological Report, 10. English Heritage, London.
• Ixer, R.A., Bevins, R.E., 2010. The petrography, affinity and provenance of lithics from the Cursus Field, Stonehenge. Wiltshire Archaeological & Natural History Magazine 103, 1-15.
• Ixer, R.A., Bevins, R.E., 2011. Craig Rhos-y-felin, Pont Saeson is the dominant source of the Stonehenge rhyolitic debitage. Archaeology in Wales 50, 21-31.
• Ixer, R.A., Bevins, R.E., Pearce, N.J.G., Dawson, D., 2022. Victorian gifts: New insights into the Stonehenge Bluestones. Current Archaeology 391, 48-52.
• Ixer, R.A., Bevins, R.E., Pirrie, D., Power, M., 2023. Treasures in the Attic. Testing Cunnington's assertion that Stone 32c is the 'type' sample for Andesite Group A. Wiltshire Archaeological & Natural History Magazine 116, 1-15.
• John, B.S., 2024a. A bluestone boulder at Stonehenge: implications for the glacial transport theory. E&G Quaternary Science Journal 73, 117-134.
• Johnson, A., 2008. Diagram of Stonehenge. Available at: https://commons.wikimedia.org/wiki/File:Stone_Plan.jpg.
• Parker Pearson, M., Bevins, R.E., Ixer, R.A., Pollard, J., Richards, C., Welham, K., Chan, B., Edinborough, K., Hamilton, D., Macphail, R., Schlee, D., Simmons, E., Smith, M., 2015. Craig Rhos-y-felin: a Welsh bluestone megalith quarry for Stonehenge. Antiquity 89(348), 1331-1352.
• Parker Pearson, M., Bevins, R.E., Pearce, N.J.G., Ixer, R.A., Pollard, J., Richards, C., Welham, K., 2022a. Reconstructing extraction techniques at Stonehenge’s bluestone megalith quarries in the Preseli hills of west Wales. Journal of Archaeological Science: Reports 46, 103697.
• Pitts, M., 2011. Bluestones on News at Ten. Mike Pitts Digging Deeper blog. https://mikepitts.wordpress.com/2011/12/20/bluestones-on-news-at-ten/.
• Pitts, M., 2022. How to build Stonehenge. Thames & Hudson.
• Thorpe, R.S., Williams-Thorpe, O., Jenkins, D.G., Watson, J., Ixer, R., Thomas, R., 1991. The geological sources and transport of the bluestones of Stonehenge, Wiltshire, UK. Proceedings of the Prehistoric Society 57, 103-157.
• Williams-Thorpe, O., Thorpe, R.S., 1992. Geochemistry, sources and transport of the Stonehenge Bluestones. Proceedings of the British Academy 77, 131-161.
• Stones of Stonehenge website: http://www.stonesofstonehenge.org.uk/2020/07/below-ground-stumps.html (accessed 2025).

 

• stumps.html (accessed 2025).