# Writing as a Self-Organized Critical Process

arXiv: https://arxiv.org/abs/2610.05466 · HTML: https://mlsanity.com/paper/2610.05466/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 53 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 6 of 6)

- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion](https://mlsanity.com/paper/1804.07745/) (2018)
- [Criticality in Formal Languages and Statistical Physics](https://mlsanity.com/paper/1606.06737/) (2016)
- [Autocorrelations Decay in Texts and Applicability Limits of Language Models](https://mlsanity.com/paper/2305.06615/) (2023)
- [States of LLM-generated Texts and Phase Transitions between them](https://mlsanity.com/paper/2503.06330/) (2025)
- [Rethinking the Relationship between the Power Law and Hierarchical Structures](https://mlsanity.com/paper/2505.04984/) (2025)

## Abstract (arXiv)

We explain autocorrelation decay power laws omnipresent in texts by self-organized criticality. Specifically, we analyze the recently released KLiCKe keystroke dataset and show that not only the final texts' autocorrelations form a manifold that adheres to a power law with a finite-size scaling, but also the text revisions generate revision-size-dependent restoring dynamics toward that manifold. Thus, human writing appears to dynamically regulate semantic correlations in a text toward a critical state.