Tootfinder

Code is a confusing engineering object for our human brains. It is a bit like building a bridge or a kitchen utensil: it’s an object without a mind, it has a function, it can fail, people do unexpected things with it. But it can also feel a bit like a person given a task: it has behavior, it •decides•, it •acts•, it •causes•.
(All arguably true of a bridge too, but most of us don’t think of bridges that way!)
The lay understanding of code leans heavily on the idea that programs are anthropomorphic, little homunculi with agency.
2/

Ten Simple Rules for Catalyzing Collaborations and Building Bridges between Research Software Engineers and Software Engineering Researchers
Nasir U. Eisty, Jeffrey C. Carver, Johanna Cohoon, Ian A. Cosden, Carole Goble, Samuel Grayson
https://arxiv.org/abs/2506.03012

Ten Simple Rules for Catalyzing Collaborations and Building Bridges between Research Software Engineers and Software Engineering Researchers
In the evolving landscape of scientific and scholarly research, effective collaboration between Research Software Engineers (RSEs) and Software Engineering Researchers (SERs) is pivotal for advancing innovation and ensuring the integrity of computational methodologies. This paper presents ten strategic guidelines aimed at fostering productive partnerships between these two distinct yet complementary communities. The guidelines emphasize the importance of recognizing and respecting the cultural …

Transformative or Conservative? Conservation laws for ResNets and Transformers
Sibylle Marcotte, R\'emi Gribonval, Gabriel Peyr\'e
https://arxiv.org/abs/2506.06194

Transformative or Conservative? Conservation laws for ResNets and Transformers
While conservation laws in gradient flow training dynamics are well understood for (mostly shallow) ReLU and linear networks, their study remains largely unexplored for more practical architectures. This paper bridges this gap by deriving and analyzing conservation laws for modern architectures, with a focus on convolutional ResNets and Transformer networks. For this, we first show that basic building blocks such as ReLU (or linear) shallow networks, with or without convolution, have easily exp…