Specimen IVPP V 13352 (Institute of Vertebrate Paleontology and Paleoanthropology, Beijing, China), the holotype of Microraptor gui (11), was examined and photographed under UV light. Images were taken on slides (Kodak Professional Elitechrome ISO 100/21° and later scanned) and with a digital SLR.

UV-A lamps with a wavelength of 365–366 nanometers were used. Powerful modern UV-A lamps guarantee a UV intensity between 4 000 and more than 90 000 microwatts per cm², depending on the distance concerned and the number of lamps. (Note that when unprotected eyes and skin are exposed to artificial UV-A of high intensity, the recommended T_max values of the manufacturers, usually between 5 and 30 minutes, must not be exceeded. In any case it is safer to cover skin of the hands and forearms with clothing and the eyes with UV-blocking glasses or goggles from the beginning of any UV investigation).

Sometimes essential details of bones and soft parts can exclusively be demonstrated by ultraviolet-light photography due to the fact that the researcher will not be able to differentiate tiny structures and differences in colour and composition under ultraviolet light with the naked eye or with a microscope. These differences are enhanced considerably by an established filtering technique which is crucial for photographic documentation. The application of different filters allows a selective visualisation of peculiar fine structures by providing additional contrast. Colour correction filters (yellows, blues and reds of different types and densities and in different combinations) are made from special coloured glass or polyester and are affixed to the camera or microscope lens. In most cases a selection of different colour correction filters is necessary. The first filter has to be a UV Filter which is supposed to block UV light up to 390 nanometers (e.g. Hama or Hoya brand O-Haze).

On each stone slab, bone or tissue will react differently to different light wavelengths and will be captured differently with varying exposures and filters - a blanket approach to formations or even horizons is not advised. This appears to be true even of plates and counterplates of single specimens in some cases, and not just more predictable differences between different horizons or formations of rock. Thus combinations of filters and lighting must be used to provide the details of the structures that are of interest. According to our experience best results are obtained for most specimens with a wavelength of 365–366 nanometers (UV-A). The optimum of filtering and exposure time has to be tested in a series of experiments [3]. The number and combination of filters varies greatly: exposure times may be between 10 seconds and 10 minutes, depending on the nature of the fossil material, the magnification and the intensity and incident angle of the ultraviolet lamps.

Recording the images work best with analogue (film) photography onto slide film although digital cameras can be used.

Some of the resultant photographs are shown in figures 2–5. Numerous other slides were made and are archived at the IVPP.

The use of UV light in addition to different filters during photography results in the various colours that are seen. These are caused by a combination of different absorption and reflectance of the various minerals that comprise the specimen and surrounding matrix or other factors. Occasional blue-white dots are dust motes that fluoresce brightly under intense UV and patches of glue/ solvents are clearly visible where parts of the slab were prepared (e.g. on the right hand side of figure 2). Figure 2 shows two different views of the specimen under different filter combinations, demonstrating the way in which some structures can fluoresce differently (or rather, be recorded differently) as a result. For example in 2B, the patch of soft tissue on the back of the neck is much duller than in 2A and can be seen more clearly as it contrasts better with the surrounding elements. In all cases, the matrix is somewhat dark. While there is variation in the colour of the matrix, the differences in tone and colour under UV are much less then in normal light, where the matrix is predominantly off-white but with darker and even black patches present.

Several features of the various tissues and especially feathers are visible under UV light, though the halo also remains visible. Under most filter regimes the bones show up as being pale green and are relatively uniform in colour and reflectance indicating homogeneous preservation of the bones (e.g. see figure 2). Large patches of indeterminate soft tissues are visible, notably around the neck, between the legs and around the pelvis and tail base (see figure 2). These can be identified as they fluoresce brightly and this suggests that they are phosphatised. Other patches of indeterminate body tissues are visible around the sternum and lower ribcage but are less bright and cannot always be seen with some filters (e.g. compare figure 2B with figure 5). Most soft tissues are associated with the skeleton but others are some distance from the bones.

The feathers are often hard to make out as they have a very low fluorescence/reflectance and thus are very dark. Longer exposures or the use of more powerful lights to boost contrast does not improve their visibility as light reflected from the bones and soft tissues can washout the image. Furthermore, in places the soft tissues overlap the feathers making identification of parts of them difficult (e.g. see figure 3). What is clear however, is that in places the feathers do extend into the halo around the bones (see figures 3 and 4 and below).

While the use of UV light does provide a better contrast between some elements of the specimen and others, it does not always reveal differences between elements of a certain kind. Thus, for example, identifying individual feathers from the mass of preserved feathers is no easier under UV than normal light.

Examination of the specimen under UV light and the resultant photographs demonstrate that the feathers of the Microraptor gui holotype extend into the ‘halo’ around the bones, in some cases as far as the bones themselves. In particular, this can be seen on the posterior face of the right metatarsus (see figure 3) and the furcula /sternal plate (figure 4). The former is especially important as it provides the confirmation of genuine attachment considered lacking by Padian and Dial [18]. In addition to this pattern being expected from how feathers articulate in modern birds (see above), this pattern matches that seen in other specimens from Liaoning, both in non-avian theropods and avians (e.g. Beipiaosaurus [34], Epidexipteryx [35] and Eoconfuciusornis [36]). This is also seen in Archaeopteryx from the Upper Jurassic Solnhofen deposits in Germany [see 1], [5]. As such we can be confident that this pattern is genuine and the feathers as preserved did extend to the bones of the specimen but are simply not visible under natural light.

The extension of the feathers into the halo and reaching the bones of the animal suggest strongly that these are in their natural position; i.e. they have not disarticulated and moved away from the body as a result of decomposition or water action. Indeed the lack of disturbance of non-primary and secondary feathers (such as those around the head and chest) indicate that the specimen was buried rapidly and suffered no great disturbance as these are normally the first to be lost during decomposition [37]. The preserved articulation of the feathers is therefore considered to be an accurate representation of their position in life. Some inferences can also be made about the orientation of the feathers, though as noted by Tischlinger and Unwin [5] care must be taken as the apparent position of the feathers in a fossil can be deceptive. Since the specimen is obviously compressed into two dimensions, the exact plane of the feathers with respect to the bones in 3D in life cannot be determined, but the relative positions of the feathers with respect to each other and the bones is likely correct.

It is clear that if the feathers have moved, they have not moved far. They retain contact with the bones of the specimen, none are significantly different from the position seen on modern birds (e.g. the feathers on the manus are subparallel to the fingers and the feathers are subparallel to each other), and none are articulated in places where they could not be present (e.g. on the unguals) or entirely separated from the skeleton. Thus, the general orientation of the feathers on the specimen is considered to be genuine, both with respect to the bones and to each other. The extension of the feathers into their halo also increases their known length, most notably with the body feathers and in places this would more double their apparent length (see table 1). Significantly, this also adds to the lengths of some long feathers of the manus and tibiotarsus as measured by both Xu and colleagues [11] and Chatterjee and Templin [19] and thus also would increase the wing areas as calculated in the latter publication.

Even under UV light the feathers remain difficult to trace, largely as a result of the presence of phosphatised tissue that cover the area of the halo in places and also between the bones of the skeleton. There is no obvious structure or pattern to this material, and it is not clear what body tissues this originally was (i.e. muscles, interstitial tissue etc.). The halo itself may also be a result of a modification of the matrix owing to a reaction with the soft tissues. In places the feathers do show up as a carbonised stain on the rock that extends into the halo, but in other places are covered and only their structure and patterns are visible (see figure 4). This phosphatised tissue is inferred as part of the original body tissues of the animal that after death disassociated from the body and drifted or settled out (or even moved by diffusion) partly away from the bones before becoming fossilised. This leaves the tissue unstructured and patchy (e.g. see figure 5) rather than in a consistent mass on the bones as seen in at least some fossils (e.g. a specimen of the basal pterosaur Anuroganthus from the Solnhofen Lithographic Limestone, Germany, [cf. 38]). These phosphatised tissues therefore obscure the carbonised feathers and make them difficult to observe close to the bones. It is therefore likely that they simply lie on top of the feathers, and these are likely preserved but simply obscured in most places.

The apparent paradox that the feathers have remained in place while some of the soft tissues have moved is not in fact real. Among extant birds soft tissues can begin to decay almost instantly with bacteria colonizing the carcass of an animal within hours of death [37], while some feathers at least may stay articulated with the carcass for weeks [39]. As such it is reasonable to note that the feathers would retain a correct position and orientation on a dead dromaeosaur while body fluids and tissues decayed and covered some parts of the feathers. Notably the phosphatised tissues lie very close to the skeletal remains of the animal, which itself is in a natural posture. It seems unlikely therefore that any parts of the specimen were disturbed after coming to rest on the substrate after the initial death and possible transport.

Based on this new evidence we suggest that future research can assume that the feathers of Microraptor gui are preserved in a natural and correct position, though are somewhat longer than are visible under natural light. It is likely that other specimens from Liaoning similarly hide the details of feathers, or perhaps even other tissues, and care should be taken when evaluating material at face value. Certainly other specimens show a similar pattern with a featherless ‘halo’ (e.g. Caudipteryx dongi) or even where feathers run to the bones in some places but not others (e.g. Longipteryx [24]). While this is perhaps not a surprising conclusion based on how feathers (and especially long flight feathers) are attached to the body of birds, it is an important confirmation of this point. Furthermore, we would suggest that unless there is good reason to think that feathers have moved significantly away from a carcass, feathers should be assumed to be in a natural articulation and reach the bones, even where a halo is present. In short, the default hypothesis for analysing fossils such as Microraptor should be that feathers reached the bones and are preserved in articulation.

Further research into the taphonomy of these deposits is strongly encouraged to determine the processes at play and what other specimens may contain hidden material. We would also encourage curators, and especially preparators, to take care with exceptionally preserved specimens as they may contain hidden information that could be lost during preparation work if UV light is not employed. Just because specimens appear to lack soft tissues does not mean that feathers, skin and more might be lurking unseen in the matrix. Equally however, the liberal use of preservatives and glues can hide important details. Thus we warn against the practice of dousing whole (if fragile) specimens in consolidants that cannot be easily removed as these can mask such cryptic soft tissues as effectively as if they had been prepared off of the matrix.