You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
First of all, thank you for the wonderful work! I’ve been using the dataset and noticed the following format:
{
"figure_id": 2,
"query": "What is the name of the line that is the furthest away from its fi value from the W_H axis?",
"answer": "lambda_L = 0.13",
"inst_category": 1,
"qa_source": 3
},
I see that inst_category has four possible values (1, 2, 3, 4). Could you please clarify what each of these categories represents?
Additionally, I noticed that while the dataset mentions charxiv and the charts it covers, it doesn’t specify the exact types of those charts. Would it be possible to provide the specific location or documentation that explains these chart types in more detail?
Thank you so much for your time and help!
The text was updated successfully, but these errors were encountered:
they correspond to text in chart, text in general, number in chart and number in general respectively.
you can look for src/constants.py for details e.g., prompts, instructions
as for chart types, we have the metadata json but probably haven't updated the codebase to aggregate results based on chart types, as we only had them during its paper rebuttal.
could you drop me an email for your needs? i'm happy to figure it out with you!
Hi there,
First of all, thank you for the wonderful work! I’ve been using the dataset and noticed the following format:
I see that inst_category has four possible values (1, 2, 3, 4). Could you please clarify what each of these categories represents?
Additionally, I noticed that while the dataset mentions charxiv and the charts it covers, it doesn’t specify the exact types of those charts. Would it be possible to provide the specific location or documentation that explains these chart types in more detail?
Thank you so much for your time and help!
The text was updated successfully, but these errors were encountered: