# Generalization and the Rise of System-level Creativity in Science

arXiv: https://arxiv.org/abs/2510.03240 · HTML: https://mlsanity.com/paper/2510.03240/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2025.

## Built on by (most cited first, 2 of 2)

- [Measuring Combinatorial Creativity in Large Language Models and Humans](https://mlsanity.com/paper/2509.21043/) (2025)
- [AI in Science: Early Insights](https://mlsanity.com/paper/2609.28504/) (2026)

## Abstract (arXiv)

Scientific progress is widely understood as combinatorial, yet existing measures focus on the inputs a paper draws together, saying little about how knowledge is supplied for downstream reuse. Analyzing citation networks from tens of millions of publications in OpenAlex and the Web of Science, we decompose scientific contributions into three functional types, foundations, extensions, and generalizations, distinguishable by the roles they play in future science. Foundational and extensional works, which build and elaborate ideas within disciplines, dominated the post-war decades but declined steadily after the 1990s, while generalizations that catalyze innovation across many contexts rose sharply. Challenging the narrative of declining innovation inferred from the disruption index, our findings suggest the locus of innovation has shifted from within disciplines to between them, a transition the Internet and large language models may have facilitated. Our indices disentangle innovation modes conflated by existing measures, enabling reinterpretation of landmark findings of 'disruptive' science.