This happened on both papers I submitted this year - approximately "Well-organized and clear evidence that the effect is real, under many conditions. But authors don't explain *why* it happens. Weak reject" I refuse to fabricate explanations... but I'm being incentivized to :(https://twitter.com/goodfellow_ian/status/1023606441096040448 …
I'm trying to think of a neural nets paper where I believed the *why* explanation. They nearly always seem, well, fabricated, to use your term. I find this frustrating enough that I wrote a short essay about it: http://neuralnetworksanddeeplearning.com/chap3.html#on_stories_in_neural_networks …
