Anthony Gitter

I don't think the problem is the size of a single manuscript file. Rather, the branch also tracks archived versions of every historical version of the manuscript we've deployed before...

https://github.com/orgs/community/discussions/35197 provides more details. The artifacts grew to 10 GB in size, which leads to the 10 min timeout @dhimmel detected. We can monitor the artifacts size from the actions...

I'm documenting my process to prune the `gh-pages` branch here. Checkout `gh-pages` locally, confirm I have the output from the last [commit](https://github.com/greenelab/covid19-review/commit/483a8dde87ca288e6d1649f658127b378e6ec24a), and create a local copy for safekeeping. ```...

The reference numbers can change with each build of the manuscript, so I'm noting here this comment refers to: Sensitive detection of rare disease-associated cell subsets via representation learning https://doi.org/10.1101/046508...

It sounds like they have a special case of convolution similar to this part of the Transformer architecture in the [Attention Is All You Need](https://arxiv.org/abs/1706.03762) paper:  Is that right?...

> this whole discussion is just around semantics Yes, I agree. I seem to recall others using the term "convolution" to describe this same operation on gene expression vectors around...

I suggest separating the two possible revisions and pull requests. Clarifying the description of CellCNN would require only a new sentence or two, which we can review and merge quickly....

@VGligorijevic if you merge, I also recommend providing the package version(s) that deepNF requires, especially `keras` and `tensorflow`.

Cross referencing #47.

Interesting conversation @dhimmel. The most relevant part of the article I posted was: > To pre-register a study, researchers lay out their hypothesis and proposed methods for data collection and...