[REVIEW]: Generating Visualizations Conversationally using LLMs

[editorialbot]

Submitting author: @buddyroo30 (Andrew Smith)
Repository: https://github.com/buddyroo30/canvasxpress_gen
Branch with paper.md (empty if default branch): JOSS-submission
Version: V1.0.1
Editor: @crvernon
Reviewers: @ahmadawais, @RahulSundar
Archive: Pending

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/280321271949ddca3d68624b431a9c47"><img src="https://joss.theoj.org/papers/280321271949ddca3d68624b431a9c47/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/280321271949ddca3d68624b431a9c47/status.svg)](https://joss.theoj.org/papers/280321271949ddca3d68624b431a9c47)

Reviewers and authors:

Please avoid lengthy details of difficulties in the review thread. Instead, please create a new issue in the target repository and link to those issues (especially acceptance-blockers) by leaving comments in the review thread below. (For completists: if the target issue tracker is also on GitHub, linking the review thread in the issue or vice versa will create corresponding breadcrumb trails in the link target.)

Reviewer instructions & questions

@ahmadawais & @RahulSundar, your review will be checklist based. Each of you will have a separate checklist that you should update when carrying out your review.
First of all you need to run this command in a separate comment to create the checklist:

@editorialbot generate my checklist

The reviewer guidelines are available here: https://joss.readthedocs.io/en/latest/reviewer_guidelines.html. Any questions/concerns please let @crvernon know.

✨ Please start on your review when you are able, and be sure to complete your review in the next six weeks, at the very latest ✨

Checklists

@ahmadawais, please create your checklist typing: @editorialbot generate my checklist

@RahulSundar, please create your checklist typing: @editorialbot generate my checklist

[editorialbot]

Hello humans, I'm @editorialbot, a robot that can help you with some common editorial tasks.

For a list of things I can do to help you, just type:

@editorialbot commands

For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:

@editorialbot generate pdf

[editorialbot]

Software report:

github.com/AlDanial/cloc v 1.90  T=2.88 s (13.9 files/s, 11137.2 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
JSON                             5              0              0          28157
Python                          17            465            203           2019
HTML                             1             38              0            265
CSS                              3             30              3            226
TeX                              1             18              0            197
Markdown                         5             52              0            136
make                             2             27              0             83
Perl                             3             16             26             68
Dockerfile                       2              4              0             22
YAML                             1              1              4             19
-------------------------------------------------------------------------------
SUM:                            40            651            236          31192
-------------------------------------------------------------------------------

Commit count by author:

    76	EC2 Default User
    33	Andrew K Smith
    10	Andrew Smith

[editorialbot]

Paper file info:

📄 Wordcount for paper.md is 1896

✅ The paper includes a Statement of need section

[editorialbot]

License info:

✅ License found: Apache License 2.0 (Valid open source OSI approved license)

[editorialbot]

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

✅ OK DOIs

- 10.48550/arXiv.2402.03216 is OK
- 10.1145/3397271.3401075 is OK
- 10.48550/arXiv.2407.21783 is OK

🟡 SKIP DOIs

- No DOI given, and none found for title: Showing Examples
- No DOI given, and none found for title: CanvasXpress: A JavaScript Library for Data Analyt...
- No DOI given, and none found for title: Better language models and their implications
- No DOI given, and none found for title: Retrieval-Augmented Generation for Large Language ...
- No DOI given, and none found for title: Long-context LLMs Struggle with Long In-context Le...
- No DOI given, and none found for title: milvus-io/pymilvus
- No DOI given, and none found for title: A Quick Intro to Leave-One-Out Cross-Validation (L...
- No DOI given, and none found for title: Hello GPT-4o \textbar OpenAI
- No DOI given, and none found for title: Meet Claude
- No DOI given, and none found for title: Large Enough
- No DOI given, and none found for title: Google AI Gemini API \textbar Google AI Studio \te...
- No DOI given, and none found for title: Phi-3 Open Models - Small Language Models \textbar...
- No DOI given, and none found for title: Introducing DBRX: A New State-of-the-Art Open LLM
- No DOI given, and none found for title: GPT-4
- No DOI given, and none found for title: OpenAI vs Open-Source Multilingual Embedding Model...
- No DOI given, and none found for title: CanvasXpress: AI using LLM

❌ MISSING DOIs

- None

❌ INVALID DOIs

- None

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[crvernon]

👋 @buddyroo30, @ahmadawais, and @RahulSundar - This is the review thread for the paper. All of our communications will happen here from now on.

Please read the "Reviewer instructions & questions" in the first comment above.

Both reviewers have checklists at the top of this thread (in that first comment) with the JOSS requirements. As you go over the submission, please check any items that you feel have been satisfied. There are also links to the JOSS reviewer guidelines.

The JOSS review is different from most other journals. Our goal is to work with the authors to help them meet our criteria instead of merely passing judgment on the submission. As such, the reviewers are encouraged to submit issues and pull requests on the software repository. When doing so, please mention #7529 so that a link is created to this thread (and I can keep an eye on what is happening). Please also feel free to comment and ask questions on this thread. In my experience, it is better to post comments/questions/suggestions as you come across them instead of waiting until you've reviewed the entire package.

We aim for the review process to be completed within about 4-6 weeks but please make a start well ahead of this as JOSS reviews are by their nature iterative and any early feedback you may be able to provide to the author will be very helpful in meeting this schedule.

[crvernon]

👋 @buddyroo30 - as an initial step, please reduce the word count of your paper to around 1000 words max. Thanks!

[buddyroo30]

Hi, Thank-you for agreeing to go ahead and review our paper and I will work to reduce the word count. However, it has been awhile since we originally submitted the paper and it was uncertain that you were actually going to review it (due to the license issues around CanvasXpress itself). Since submitting we have actually made additional significant progress on this project, and if possible we'd like to update the paper to include our updated content and results. So I'm thinking I'll do that as part of reducing the word count, and I hope that is okay --- but please let me know if you have any concerns. best regards,Andrew On Monday, November 25, 2024 at 11:12:14 AM EST, Chris Vernon ***@***.***> wrote: 👋 @buddyroo30 - as an initial step, please reduce the word count of your paper to around 1000 words max. Thanks! — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: ***@***.***>

[crvernon]

A-OK @buddyroo30

[buddyroo30]

Great, thanks. I am out the rest of this week on vacation, but will work on this next week and get you the updated paper soon. On Monday, November 25, 2024 at 06:39:09 PM EST, Chris Vernon ***@***.***> wrote: A-OK @buddyroo30 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: ***@***.***>