weekly-papers-2026-10-24

Two plots: target-logit gradient magnitude versus logit margin dropping to zero at a precision cliff, and distillation gradient norm plateauing at a noise floor

A Fix for Softmax and Cross-Entropy

Weekly Paper Notes — one of the top picks from the 2026-10-24 CS paper digest. Area: AI / ML. Authors: Jonathan T. Barron, Dan Gnanapragasam, Michael Tschannen (Google DeepMind) arXiv: 2610.31642 · PDF TL;DR Every deep learning framework computes softmax and cross-entropy the same way: subtract the largest logit so exp can’t overflow, then normalise. That trick fixes overflow and leaves two quieter bugs in place. The first, which the authors call Softmax Collapse, hits when the model is very confident....

AI-greement harness: protocol knowledge base, modular consensus skeleton, and Lean verification framework, connected by a researcher-developer-verifier loop

The End of Consensus Research?

Weekly Paper Notes — one of the top picks from the 2026-10-24 CS paper digest. Area: Distributed Computing. Authors: Clément Burgelin, Rachid Guerraoui, Zicong Hong, Yinan Hu, Anne-Marie Kermarrec, Rafael Pires, Rasmus Moorits Veski, Martijn de Vos (EPFL; alphabetical order) arXiv: 2610.30114 · PDF TL;DR The title asks a question and the last section answers it: “Our answer is no; this is just a new beginning.” The EPFL distributed computing group asks whether a coding agent can produce a practical new consensus protocol: designed, implemented, benchmarked under geo-replication, crash-tested and proved safe....

Top: a page reference string with a sliding window of the last τ references defining the working set. Bottom: useful work versus number of programs, collapsing past the point where working sets exceed memory unless load control holds extra programs back.

The Working Set Model for Program Behavior (Denning, 1968)

Weekly Paper Notes — the Seminal Paper of the Week for the 2026-10-24 digest. Area: Operating Systems. Author: Peter J. Denning (MIT Project MAC) Published: Communications of the ACM 11(5), May 1968, pp. 323–333. DOI: 10.1145/363095.363141. First presented at the first ACM Symposium on Operating Systems Principles, Gatlinburg, 1967. Why the paper still matters In the mid-1960s, paging was new and it was misbehaving. Machines like Atlas, the IBM 360/67 and the GE 645 running Multics could keep more programs in memory than would fully fit, by paging the parts not in use out to drum or disk....