# The Differential Meaning of Models: A Framework for Analyzing the Structural Consequences of Semantic Modeling Decisions

arXiv: https://arxiv.org/abs/2509.00248 · HTML: https://mlsanity.com/paper/2509.00248/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 29 Aug 2025.

## Builds on (most cited first, 9 of 9)

- [Similarity of Neural Network Models: A Survey of Functional and Representational Measures](https://mlsanity.com/paper/2305.06329/) (2023)
- [The Geometry of Culture: Analyzing Meaning through Word Embeddings](https://mlsanity.com/paper/1803.09288/) (2018)
- [Benchmarks as Microscopes: A Call for Model Metrology](https://mlsanity.com/paper/2407.16711/) (2024)
- [How Many Topics? Stability Analysis for Topic Models](https://mlsanity.com/paper/1404.4606/) (2014)
- [How we do things with words: Analyzing text as social and cultural data](https://mlsanity.com/paper/1907.01468/) (2019)
- [Provocations from the Humanities for Generative AI Research](https://mlsanity.com/paper/2502.19190/) (2025)
- [Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale](https://mlsanity.com/paper/2505.23785/) (2025)
- [Cultural Cartography with Word Embeddings](https://mlsanity.com/paper/2007.04508/) (2020)
- [Semiotic Complexity and Its Epistemological Implications for Modeling Culture](https://mlsanity.com/paper/2508.00095/) (2025)

## Abstract (arXiv)

The proliferation of methods for modeling of human meaning-making constitutes a powerful class of instruments for the analysis of complex semiotic systems. However, the field lacks a general theoretical framework for describing these modeling practices across various model types in an apples-to-apples way. In this paper, we propose such a framework grounded in the semiotic theory of C. S. Peirce. We argue that such models measure latent symbol geometries, which can be understood as hypotheses about the complex of semiotic agencies underlying a symbolic dataset. Further, we argue that in contexts where a model's value cannot be straightforwardly captured by proxy measures of performance, models can instead be understood relationally, so that the particular interpretive lens of a model becomes visible through its contrast with other models. This forms the basis of a theory of model semantics in which models, and the modeling decisions that constitute them, are themselves treated as signs. In addition to proposing the framework, we illustrate its empirical use with a few brief examples and consider foundational questions and future directions enabled by the framework.