Daniel Ecer

Maybe it would be good if the consolidation was more conservative. e.g. check the year and all of the authors that appear in the reference.

Hi @kermitt2 I was using the default Crossref consolidation. I didn't want to commit to setting up biblio-glutton just now. Maybe it could be configuration option what to optimize for....

Okay, fair enough. I like convenience, but maybe it's not practical in this case. In that case, I guess it will be better to close this issue?

Thank you for the quick feedback. Personally I find every additional model adds a certain amount of overhead. Not just in terms of code, more so with preparing the training...

Yes, for me the main use-case would also look like that. Mainly with docker / container (but not strictly). There would be a default configuration and environment variables make it...

I guess you could include a default config file with all of the placeholders in Docker Hub? Sub-projects would need to do the same, or anyone with a different default...

I haven't looked into it yet. I imagine it not being trivial. I believe I have seen detection based on the font name elsewhere. In some cases even via a...

Thinking about it, I have some vague recollection someone at the GROBID camp in Paris was going to work on something related. Perhaps Pedro? I am probably just making it...

> Hi Daniel, > > For the white image, it's probably the same as what I raised here: [kermitt2/grobid#826](https://github.com/kermitt2/grobid/issues/826) > > I think these are the "Soft-Mask" images of the...

BTW the way I found those is by looking at regressions of using my models with the new version of GROBID vs previous version. This affected the title extraction using...