PONE-D-23-39546A supervised multiclass framework for mineral classification of Iberian beadsPLOS ONE

Dear Dr. Sanchez-Gomez,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

 

As you will see, the reviewers are generally positive about the analytical integrity of the work and your underlying technical methodology, but highlight several significant issues with the manuscript in its current form. One of their most substantial concerns is the applicability of this research both in terms of extracting social meaning with regard to your own dataset and with regard to the further applications of the method and model developed herein. In particular, Reviewer 1 draws attention to your own uncertainty about what new insights the method has brought in terms of archaeological interpretation of the dataset. This calls for a substantial reconsideration of how you present your analyses, results and their wider relevance beyond this specific exercise. Sentences that Reviewer 1 highlights, but more generally the tone of the narrative, that imply your results are “wrong” may benefit from reconsidering how you frame your evaluation if you believe your results have value and are more than simply “wrong”. The value in addressing archaeological questions with the aid of this model should be more coherently justified. Overall, this study has potential and a substantial reframing of its relevance and potential impact alongside addressing specific reviewer concerns will be required before reconsideration for publication.

Please pay particular attention to required changes. These include demonstrating how your results are meaningful and as well as rephrasing, explaining more clearly what you mean when you say that aspects of the results were wrong and the means through which this was overcome within your model. 

You must also clarify the relevance and potential impact of the model as a stand alone approach. If the opinion of the analyst remains paramount to the final outcome, in which ways has the model contributed to understanding? This requires a reconsideration of the context and potential implementation of the model developed and overall, how this is presented. 

The real-world utility of the model needs to be considered with regard to studies of various scales, from individual field projects to museum-based projects using larger datasets. 

The datasets / spreadsheets need more complete captioning, explanation, labelling and to be more coherently integrated into the discussion of analyses (e.g. the number of objects ultimately studied).

Please submit your revised manuscript by Mar 03 2024 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Barry Molloy

Academic Editor

PLOS ONE

Journal requirements:

1. When submitting your revision, we need you to address these additional requirements.

Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at 

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and 

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf.

2. In your manuscript, please provide additional information regarding the specimens used in your study. Ensure that you have reported human remain specimen numbers and complete repository information, including museum name and geographic location. 

If permits were required, please ensure that you have provided details for all permits that were obtained, including the full name of the issuing authority, and add the following statement:

'All necessary permits were obtained for the described study, which complied with all relevant regulations.'

If no permits were required, please include the following statement:

'No permits were required for the described study, which complied with all relevant regulations.'

For more information on PLOS ONE's requirements for paleontology and archeology research, see https://journals.plos.org/plosone/s/submission-guidelines#loc-paleontology-and-archaeology-research.

3. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match. 

When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section.

4. Thank you for stating the following financial disclosure: 

 [This research has received resources from the Fundação para a Ciência e Tecnologia de Portugal (www.fct.pt) in the framework of the doctoral grant (UI/BD/154365/2023) awarded to (DSG) and from the Spanish Ministry of Science and Technology through the research project (PID2021-124421NB-I00) (https://investigacion.us.es/sisius/sis_proyecto.php?idproy=33567) whose PI is (CO) and the research team is composed by (JMMB), (GRG), and (JAGC). The other authors report no funding for participation in this project. ].  

Please state what role the funders took in the study.  If the funders had no role, please state: ""The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."" 

If this statement is not correct you must amend it as needed. 

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf.

5. We note that Figure 1 and 4 in your submission contain [map/satellite] images which may be copyrighted. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For these reasons, we cannot publish previously copyrighted maps or satellite images created using proprietary data, such as Google software (Google Maps, Street View, and Earth). For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright.

We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission:

a. You may seek permission from the original copyright holder of Figure 1 and 4 to publish the content specifically under the CC BY 4.0 license.  

We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text:

“I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.”

Please upload the completed Content Permission Form or other proof of granted permissions as an ""Other"" file with your submission.

In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].”

b. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only.

The following resources for replacing copyrighted map figures may be helpful:

USGS National Map Viewer (public domain): http://viewer.nationalmap.gov/viewer/

The Gateway to Astronaut Photography of Earth (public domain): http://eol.jsc.nasa.gov/sseop/clickmap/

Maps at the CIA (public domain): https://www.cia.gov/library/publications/the-world-factbook/index.html and https://www.cia.gov/library/publications/cia-maps-publications/index.html

NASA Earth Observatory (public domain): http://earthobservatory.nasa.gov/

Landsat: http://landsat.visibleearth.nasa.gov/

USGS EROS (Earth Resources Observatory and Science (EROS) Center) (public domain): http://eros.usgs.gov/#

Natural Earth (public domain): http://www.naturalearthdata.com/

6. We note that Figure 2 and 3 in your submission contain copyrighted images. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright.

We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission:

a. You may seek permission from the original copyright holder of Figure 2 and 3 to publish the content specifically under the CC BY 4.0 license. 

We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text:

“I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.”

Please upload the completed Content Permission Form or other proof of granted permissions as an ""Other"" file with your submission. 

In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].”

b. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only.

Academic Editor Comments:

1) If permits were required, please ensure that you have provided details for all permits that were obtained, including the full name of the issuing authority, and add the following statement:

'All necessary permits were obtained for the described study, which complied with all relevant regulations.'

If no permits were required, please include the following statement:

'No permits were required for the described study, which complied with all relevant regulations.'

In your manuscript, please provide additional information regarding the specimens used in your study. Ensure that you have reported specimen numbers and complete repository information, including museum name and geographic location.

For more information on PLOS ONE's requirements for paleontology and archaeology research, see https://journals.plos.org/plosone/s/submission-guidelines#loc-paleontology-and-archaeology-research.

2) We note that Figures 1 and 4 in your submission contain [map/satellite] images which may be copyrighted. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For these reasons, we cannot publish previously copyrighted maps or satellite images created using proprietary data, such as Google software (Google Maps, Street View, and Earth). For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright.

We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission:

a. You may seek permission from the original copyright holder of Figures 1,3,4,5,8,9 and 12 to publish the content specifically under the CC BY 4.0 license.

We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text:

“I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.”

Please upload the completed Content Permission Form or other proof of granted permissions as an "Other" file with your submission.

In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].”

b. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only.

The following resources for replacing copyrighted map figures may be helpful:

USGS National Map Viewer (public domain): http://viewer.nationalmap.gov/viewer/

The Gateway to Astronaut Photography of Earth (public domain): http://eol.jsc.nasa.gov/sseop/clickmap/

Maps at the CIA (public domain): https://www.cia.gov/library/publications/the-world-factbook/index.html and https://www.cia.gov/library/publications/cia-maps-publications/index.html

NASA Earth Observatory (public domain): http://earthobservatory.nasa.gov/

Landsat: http://landsat.visibleearth.nasa.gov/

USGS EROS (Earth Resources Observatory and Science (EROS) Center) (public domain): http://eros.usgs.gov/#

Natural Earth (public domain): http://www.naturalearthdata.com/

3) Please provide details on copyright permissions for all images of objects reproduced in the figures and for all illustrations.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: The main aim of the study presented in this manuscript is to use machine-learning algorithms to achieve mineralogical classifications of prehistoric beads. The use of this computational technique is presented as suitable in cases where the application of analytical methods other than portable XRF is not feasible. In general, the aim and execution of the exercise is original and potentially innovative, as it presents a new way to look at the classification of beads in terms of mineralogical composition. However, there remain serious doubts as to the overall efficiency and meaningfulness of the results.

To begin with, in page 15 of the manuscript, the authors themselves admit that “the chemical complexity of raw materials reflected in compositional data tends to form overlapping clusters that make it challenging to establish clear boundaries between classes, which obscures the process of model selection with this type of logic”. Later, in page 19, they go on to admit that “even if the results are strictly wrong, they are very close to an accurate characterization of the samples”. This is a remarkable statement in a number of ways. The authors claim that their results are wrong. The same idea is conveyed further on, in page 27: “Thus, though strictly wrong, the prediction was quite accurate”.

These statements raise question as to how the results of the computational classification are assessed or verified. How do the authors know the results are wrong? No explanation is provided of the criteria by which the results are assessed. And then, if the results are wrong, what is the point of the exercise, anyway? Immediately after admitting that the results are wrong they claim that “they are very close to an accurate description of the samples” (page 19). If the authors have a pre-ordained understanding of what is the right and wrong classification, what is the point of a computerised model that provides a result deemed essentially wrong? And how do they know it is wrong?

The confusion stemming from these statements is further compounded in page 29, when it is claimed that “Ultimately, the model’s predictions may nicely complement the decision-making process of labelling a sample, which is, after all, up to the analyst”. A clearer definition of the intended meaning of “labelling” is also required here, but if we take it to mean “classification”, then the inevitable question is: if the task of classifying the beads according the mineralogy lies basically with the analyst, what is the point of the whole computational model?

A much clearer justification of the validity and worthiness of the whole exercise is required, because otherwise it might appear a futile.

Minor corrections

Line 114: “for the identification of bead-forming minerals” sounds a bit odd, as if the minerals had an “intention” to form beads.

Line 119: where it says “two sample sets of different sites” it should say “two sample sets from different sites”

Line 125: it should say “millennia”

Line 277: where it says “our problem” it should say “our case study”

Line 305: the meaning of the term “pipeline” in the context of machine-learning algorithms should be explained, as readers not familiar with these computational models will not be familiar with it.

Line 358: The whole paragraph is duplicated

Line 376. Table 7 is too long. It should be presented as supplementary data.

Line 459: “bead carving” should be “bead making”

Line 468: This paragraph should go much earlier on in the paper, in the introduction.

Reviewer #2: The study tests and explores the potentials of using a machine learning / multiclass model for the identification of minerals in beads from the Iberian Peninsula.

The text is well written. The authors present the protocols and methodology in detail, and importantly the limitations for the algorithm.

Archaeology is still in the rather early stages of adopting machine learning methods widely (compared to other fields), and in this context the study has value. However, certain aspects of the paper are not clear. I would advise reconsideration of a few aspects before publication.

Firstly, the paper mentions a database of more than 1k objects, but in reality, a much smaller sample is used for this proof-of-concept study case. I understand that the skewed sample (with ca. 800 variscite beads) needs to be adjusted for training the model. However, as of now, my impression is that the 1.2k bead database is not relevant to the resulting model, and I do not see why it should be mentioned in the paper. The authors should highlight which are (if any) the contributions of the 1.2k bead database in the success of the model. Otherwise, I would exclude this aspect altogether.

Secondly, even though the authors present a road map for using their model, my general critique is that I would like to see suggestions for a real-life scenario where the applicability of the model by relevant researchers in the field would be realistic and timewise sensible. For example, how many such ornaments are expected to be found on a typical site? Would this number justify the use of the model (which would require a specialised person)? In the hypothetical case of an assemblage of some 30 beads from a site, wouldn’t it be possible to scan them with the pXRF and gauge their mineralogy based on the compositions? Which is what is also suggested by the authors in the case of doubtful results. If this model is destined for large museum collections, could this proof-of-concept be tested against the whole 1.2k database (and include the results in the publication)?

Finally, it is not clear if this model is trained only for the Iberian Peninsula and / or only for this type of objects. Would the model be able to identify an unknown material (insteady of mislabelling it)? Please add specific information about the spectrum of applicability of this ML trained model.

Additional comments on supplementary data provided:

S1. Database:

1. Each tab needs a table caption explaining the variables and info included in the tab. Indicate if elements are presented as such or as compounds (considering the analysis of minerals) and justify your choice.

2. Numbers are stored as text making it difficult to judge the data. Please convert to numbers.

3. Values below the detection limits are not indicated. Only include the significant decimal places (pXRF will give many decimals that don't mean much).

4. Include the analysis of the standard materials with statistical information about their precision and accuracy, and respective detection limits.

5. In the proof-of-concept tab, the xrd3 column is empty – why is that?

S2. Ground truth – Add text that explains the graphs.

As a bottom line, I would encourage the authors to add some more emphasis on the real-life applicability of this model and pay some more attention to the treatment and presentation of the database of pXRF values.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

PONE-D-23-39546R1A supervised multiclass framework for mineral classification of Iberian beadsPLOS ONE

Dear Dr. Sanchez-Gomez,

Thank you for re-submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but still does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

==============================

Thank you for your revised manuscript and for your careful attention to the comments by the reviewers and the editor of your original submission. To be accepted for publication, please reconfigure your datasheet paying close attention to the reviewer's commentary. This is essential for clarity and for accessibility. There are instances in the text where stating clearly the analytic results, including specific data, will better support your argument or require rewording of your argument to a position that is fully grounded in the data. There is capacity to demonstrate greater awareness of the limitations of portable XRF and the reviewer highlights some important elements with regard to data management, though it would be advisable to pay close attention throughout the text to issues they specifically highlight and other areas where critical awareness of those limits can make your argument more convincing. I look forward to considering a revised version of the manuscript that addresses these minor points for revision. 

==============================

Please submit your revised manuscript by May 11 2024 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Barry Molloy

Academic Editor

PLOS ONE

Journal Requirements:

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

Additional Editor Comments:

Thank you for revising your manuscript and paying close attention to the comments by both reviewers and by the editor. This version has substantially improved as a result and in most respects is suitable for publication. However, there are a few important amendments that are required before this can be accepted for publication. These primarily relate to how you present and employ your data generated with a portable XRF. I would ask you to pay close attention to the the specific details of the reviewer comments and to the wider implication of these with regard to systematic presentation and clarity, supported by data, when discussing your results.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #2: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #2: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #2: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #2: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #2: I appreciate the changes made to the text by the authors. I believe the paper in its revised form reflects more accurately the scope and aims of the study, and highlights more substantially the value of this model to the discipline. I, however, have a few additional comments for the authors to pay attention to, which I believe will strengthen the study.

Regarding S1 and S2:

1 --- Proof-of-concept tab -> S1_Database

The Proof-of-concept tab in the S1_Database file should be curated. As of now, there is what I can best describe as a raw XRF data dump. Numbers should be stored as such (they are stored text as of now, as they were with the original submission) and only the important decimals should be included, unless the authors suggest accuracy of the pXRF to 0.00000001.

For example, the value 1.5975651858007571 should be stored as 1.6. One decimal place for a value >1 % is sufficient for pXRF data and shows understanding of the technique and its limitations.

2 --- pXRF_LOD -> S1_Database

In pXRF_LOD in S1_Dataset, please explain how you got to those LODs. From what I can understand, one CRM has been analysed: BCR32.

As an example, the authors report an LOD for Co of 0.00001. How did you get to this? This is extremely low for pXRF. This is just one example. There are more LODs that need explanation.

3 --- Ref_Material_Stats -> S1_Database

In the Ref_Material_Stats tab please show clearly the measured versus certified values (e.g. in a row just above above the mean values of the 45 measurement). As of now it is impossible to judge. Also explain your LODs for the elements not included in the CRM.

Elements not detected should not be included.

It is not clear to me how the elements to oxides conversion tables fit in this tab (which is dedicated to the certified reference material stats.

In the same tab, report data either in wt% or in ppm. Please avoid scientific formats. This will make your data much more easy to read and will add strength to your study.

4 --- Reference_Material -> S1_Database

Why include all the elements that were not detected?

5 --- S2_Table

All tables in this file need detailed captions.

In-text comments (revised manuscript):

- Lines 114-155: 1) A typical handheld pXRF has a standard spot area (ellipse in shape) of ca. 3 mm in its longest side. This is a large enough area to offer representative data for a bead. Unless the bead is made of minerals containing crystals and feldspars >3 mm. 2) Additionally, what does relative superficiality mean in the context of this sentence? Superficiality of analysis area? That would depend on the sample (cut samples can be analysed). Superficiality in terms of data quality? This takes me back to a reported LOD for CO that is way too low to be realistic. Overall, this sentence seems to be purposefully vague. Please revise showing a solid understanding of the evaluation of handheld pXRF analyses.

- Line 126: Replacing “10k beads” with “some thousands of beads” takes away credibility from the text. Just state how many beads you analysed and keep it simple. Avoid vagueness.

- Line 133: MS is (not are) unless Machine learning is meant to be plural here.

- Lines 133-138: Though not strictly wrong, this paragraph reads as rather vague (again). It would be nice to have it with more relevance to the specific study at hand.

- Line 231: How and why were <lod an="" by="" guess="" informed="" replaced="" values="">

- Line 463: A small change, nevertheless an important one: “two completely different sites” -> why not just write “two sites” and avoid unnecessary wordiness. This is an example. Similar comments apply throughout the text.

- Line 563: Do you mean the archaeology of personal adornments in general or those made by minerals such as the beads? Personal adornments can be made from a variety of materials.

Once these comments are addressed, I am happy to see this study in print.</lod>

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #2: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

A supervised multiclass framework for mineral classification of Iberian beads

PONE-D-23-39546R2

Dear Dr. Sanchez-Gomez,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Barry Molloy

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments: