Lucas Massemin

Nice, thank you ! If I find time, I can push a very basic PR

Could we simply call the [listMessages endpoint](https://platform.openai.com/docs/api-reference/messages/listMessages) to initialize the messages array, and when the threadId changes ? Happy to open a PR

- The following insights were derived [from looking for '.groups' in the repo](https://github.com/freelawproject/eyecite/search?q=.groups) - The reporter is not used in resolve for [shortcase citations](https://github.com/freelawproject/eyecite/blob/743b3b3ac2531f1910ad425334e86abe0c6e0ca9/eyecite/resolve.py#L127), nor in any other resolve method...

@mattdahl thanks for the explanation. I don't see why it would not be possible to "correct" the reporter in the [__post_init__](https://github.com/freelawproject/eyecite/blob/main/eyecite/models.py#L79) function just after self.groups is set, but modifying the...

Noted 👍 By the way, what do you think of the corner cases of the corrected_citation ? Any chance that we get them fixed in the near future ?

Created the PR

Whoops, it seems like we have another problem with the comparison hash. My colleague @alessandro-ciffo found that the comparison hash changes every time you run a new script. The following...

Hey, thanks for the quick reply. @mlissner Indeed, the idea is to build a training set for some machine learning application. I took note of your method, it's ok if...

@mattdahl Thanks ! Maybe we should consider moving away from exact string matching and use simple regex instead ? For instance in `r'\s*pa\s*super\s*'`, we would not be dependent on the...

I understand, regexes are powerful but scale badly. Well, the equivalent in python here would be to remove all punctuation and spaces, and then look for 'pasuper'. I think the...