When will the results be available for the first checkpoint, which was on 30.11.2024?

[soviet-manfred]

I thought that the results are already computed during the submission, and only must be revealed to the competitors.

[enzo]

We are a little behind schedule. They will be available on Monday.
This leaves more time over the weekend for the people who have just joined.

[soviet-manfred]

Thank you.

[soviet-manfred]

Sorry, why are the results not revealed ?

[enzo]

Last minute problem was discovered, an announcement will be made today.

[soviet-manfred]

Sorry, but ‘today’ from your last reply was on Tuesday. Was checkpoint 1 canceled somehow ?

[enzo]

Sorry for the delay, the last-minute bug required more thought than expected.

@many-kalin has raised his voice against one of our potential fixes:

Re-apply normalization

Hi, I was reviewing the code base for the challenge and noticed a function that enforces log1p normalization on the predictions in the scoring scheme: feat(broad-1/scoring): re-apply normalization if necessary · crunchdao/competitions@3d72103 · GitHub. I would argue that this step may not be necessary or desirable. Introducing normalization based on the sum of all predictions could create a dependence on the predicted variables. This might be problematic if the gene expressions for different ge…

We are waiting for the final decision before we compute anything.