-
Notifications
You must be signed in to change notification settings - Fork 12
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Reorganize proof that discrete types are Segal #137
Conversation
@TashiWalde this is great. I'll look at everything more detail this evening. I'm the one who wrote the original formalization of [RS17, 7.3] and don't mind if that proof is replaced by the improved one. What do others think @jonweinb? One more question: will this cause problems for @StiephenPradal 's open PR? If so, I'd appreciate guidance on how best to merge them. |
All of the changes to |
@TashiWalde I may have messed something up by merging your later pull request before this one. Let me know if you'd like me to revert that. I was delaying this because I wanted to give others a chance to weigh in on the duplicated proof. Maybe we merge a version with both proofs now and then open a new PR to cut the old one? Or you can go ahead and cut that out now if you prefer. |
@emilyriehl I have resolved the merge conflict. It was not your fault; I had made a non-compatible change in another pull-request. From my side the PR is now ready to be merged. I'll leave it up to you if you want to keep or discard the original proof. There is also no real hurry in merging this PR, so we can leave time for others to weigh in. |
Let's merge this now and we can make further changes later. I'm glad to hear the merge conflict wasn't my fault this time ;) |
Currently there are two completely independent proofs that every discrete type is Segal:
The second proof has many advantages over the first:
I have therefore made the following changes:
left fibration -> inner fibration
to07-discrete
. This mirrors how inner anodyne shape inclusions are defined in05-segal-types
.08-covariant
.)Discrete types are Segal types (original proof of RS17)
. The constructed term is renamed tois-segal-is-discrete'
. We can consider deleting it unless some of the intermediate calculations are deemed to still be useful.