Julian Eisenschlos

Hi @sbhttchryy , thanks for your interest 1. I suggest you use one of the [notebooks](https://colab.research.google.com/github/google-research/tapas/blob/master/notebooks/wtq_predictions.ipynb) have examples on how to convert the data into the required format in tf...

Hello @sophgit in order to help you better, can you share the logs of both of those errors you describe? Even better, if you can share a colab that reproduces...

Hello @sbhttchryy , Sorry for the delay. One thing confusing me besides the inconsistent predictions is that in theory the model should never output a prediction coordinate that is out...

Hi Niels, I think it could make sense to increase or remove entirely the answer_loss_cutoff as you have done when fine-tuning. Specially in a single batch experiment as you are...

You definitely don't want to set it to zero, since in the code it's checked for None only, that means that using zero out would effectively prohibit the training. I...

Thanks for flagging, we have fixed the issue and will be uploading an updated version of the code soon

Hey Blazej, I updated the other issue with a solution, can you let me know if that fixed the issue or you still cannot reproduce the results?

Currently newly created claims will not show on other users feed automatically/immediately. We have the concept of a workflow which is a list of pairs of claims to vote on...