Paper

Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry

Unreadunread

AI summary

arXiv:2605. 16325v1 Announce Type: new Abstract: Phase-transition phenomena in deep learning (grokking, emergent capabilities, and ontological reorganization under context shift) have been studied through several lenses, including representational compression, singular learning theory, and information-theoretic progress measures.

Reading status

Priority

About this paper

Authors: Truong Xuan Khanh
Released: 2026-05-19 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, class, under, alignment, alpha, line, rate, candidate. Source: arxiv cs.LG (Machine Learning).
arXiv: 2605.16325

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.