[CI-Work] Question about data availability

Open
#15 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
30/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Quiet
Domain
data

Research direction

Start by reading the README and checking the referenced data/seed/raw_seed.jsonl path, then verify where the 125 seeds and downstream artifacts are expected to come from. Done means documenting a data-release plan or making the requested benchmark files available so the evaluation can be reproduced.

Written by the indexing model from the issue text.

Description

Hi CI-Work authors,

Thanks for the great work and for releasing the code and prompt templates.

I was trying to run the evaluation pipeline and noticed that the data files (e.g., data/seed/raw_seed.jsonl) aren't in the repo.
The links in the README (https://aka.ms/ci-work and https://aka.ms/ci-work-code) both seem to point back to this code repo, and I couldn't find a separate data release.

Is there a plan to release the benchmark data? Ideally:

  1. The 125 task-oriented seeds (raw_seed.jsonl) used in the paper.
  2. Optionally, the downstream artifacts (enriched seeds, case episodes, formatted instructions) so people can run the trajectory evaluation directly without regenerating everything.

Either would be very helpful for reproducing the results.

Thanks!

Dominant language
Jupyter Notebook
Stars
41
Forks
8
PR merge metrics
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from microsoft/ACV

All issues in microsoft/ACV

Similar issues

More Data Engineering issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.