Skip to content

Revise Provenance Issues#6

Open
egrace479 wants to merge 3 commits into
mainfrom
egrace479-patch-1
Open

Revise Provenance Issues#6
egrace479 wants to merge 3 commits into
mainfrom
egrace479-patch-1

Conversation

@egrace479

@egrace479 egrace479 commented Feb 12, 2026

Copy link
Copy Markdown
Member

This PR works to resolve provenance issues in the repository presentation:

  • The citation file is set to match descriptions for this repository, with identifiers pointing here and at the paper where appropriate.
    • Date can be set when it is ready for a release.
  • Dataset source provenance clarifications and attribution:
    • I have revised sections in the citation to point to the actual datasets and included both their official names and a reference of the names used in this repo and the paper.
    • [TODO]: It is unclear how to reproduce the work done here due to alignment issues within the included metadata and notebooks, including references to files that don't seem to be publicly available (see issue Provenance of CanonBeetles.csv #4 & Alignment to Original Source datasets for Reproducibility #5 discussions). This needs to be resolved for reusability and reproducibility of this work.

Include dataset names and links to them (with clarification of how they're referenced here).
@egrace479

Copy link
Copy Markdown
Member Author

@SMRayeed, let's get the Citation and source dataset link fixes I made merged (please review), and you can open a new PR with the Todo:

@egrace479
egrace479 requested review from SMRayeed and hlapp May 13, 2026 14:14
@egrace479 egrace479 linked an issue May 13, 2026 that may be closed by this pull request
@egrace479
egrace479 marked this pull request as ready for review June 10, 2026 22:07
@egrace479

Copy link
Copy Markdown
Member Author

@SMRayeed, please review as we've discussed. This minimum fix really needs to be applied.

@hlapp hlapp left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

See inline edits and question (the response to which is hopefully easy).

Comment thread CITATION.cff Outdated
Comment thread README.md
# BeetleVerse

**BeetleVerse** is a benchmark suite for evaluating vision models on ground beetle classification. It provides datasets, evaluation notebooks, and results for genus- and species-level classification, domain adaptation, sample-efficient probing, and multimodal extensions. This repository accompanies the paper: [BeetleVerse: A study on taxonomic classification of ground beetles](https://doi.org/10.48550/arXiv.2504.13393).
**BeetleVerse** is a benchmark suite for evaluating vision models on ground beetle classification. It provides evaluation notebooks and results for genus- and species-level classification, domain adaptation, sample-efficient probing, and multimodal extensions for existing datasets. This repository accompanies the paper: [BeetleVerse: A study on taxonomic classification of ground beetles](https://doi.org/10.48550/arXiv.2504.13393).

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

By for existing datasets do you mean any existing datasets, or is for select datasets (or for the select datasets listed below) what you really mean?

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I was trying to say for the already published datasets, since this isn't actually introducing new datasets, but it read like that in a few places.

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe specify by saying sth like " .. for four published beetle datasets."

Comment thread README.md Outdated
Co-authored-by: Hilmar Lapp <hlapp@drycafe.net>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

README including citation is missing

3 participants