← back · blog
Notes from the margins
Short essays, half-baked observations, and the occasional rant — mostly about representation learning, ML systems, and the small habits that decide whether a result reproduces. Updated erratically; please assume drafts.
01 : Posts
-
Pre-registration changed how I read my own results
Notes on the small ritual that made our BlackboxNLP submission more defensible — including the one pre-registered hypothesis we cleanly failed, and why that failure ended up being the most interesting result in the paper.
Want to argue with one of these? — atonmoy27@wabash.edu. RSS feed coming whenever I get around to it.