# Revisiting the Platonic Representation Hypothesis: An Aristotelian View

arXiv: https://arxiv.org/abs/2602.14486 · HTML: https://mlsanity.com/paper/2602.14486/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 16 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [What is being transferred in transfer learning?](https://mlsanity.com/paper/2008.11687/) (2020)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning](https://mlsanity.com/paper/2103.01913/) (2021)
- [Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth](https://mlsanity.com/paper/2010.15327/) (2020)
- [Similarity of Neural Network Models: A Survey of Functional and Representational Measures](https://mlsanity.com/paper/2305.06329/) (2023)
- [Generalized Shape Metrics on Neural Representations](https://mlsanity.com/paper/2110.14739/) (2021)
- [PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding](https://mlsanity.com/paper/2504.13180/) (2025)
- [Do Vision and Language Encoders Represent the World Similarly?](https://mlsanity.com/paper/2401.05224/) (2024)
- [Understanding the Emergence of Multimodal Representation Alignment](https://mlsanity.com/paper/2502.16282/) (2025)
- [Deconfounded Representation Similarity for Comparison of Neural Networks](https://mlsanity.com/paper/2202.00095/) (2022)
- [ReSi: A Comprehensive Benchmark for Representational Similarity Measures](https://mlsanity.com/paper/2408.00531/) (2024)
- [Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks](https://mlsanity.com/paper/2405.01012/) (2024)
- [What Representational Similarity Measures Imply about Decodable Information](https://mlsanity.com/paper/2411.08197/) (2024)
- [With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You](https://mlsanity.com/paper/2506.16895/) (2025)
- [Disentangling the Factors of Convergence between Brains and Computer Vision Models](https://mlsanity.com/paper/2508.18226/) (2025)
- [Evaluating Representational Similarity Measures from the Lens of Functional Correspondence](https://mlsanity.com/paper/2411.14633/) (2024)
- [Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts](https://mlsanity.com/paper/2502.18710/) (2025)
- [Dynamic Reflections: Probing Video Representations with Text Alignment](https://mlsanity.com/paper/2511.02767/) (2025)
- [Estimating Neural Representation Alignment from Sparsely Sampled Inputs and Features](https://mlsanity.com/paper/2502.15104/) (2025)

## Built on by (most cited first, 30 of 44)

- [There Will Be a Scientific Theory of Deep Learning](https://mlsanity.com/paper/2604.21691/) (2026)
- [Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale](https://mlsanity.com/paper/2604.18572/) (2026)
- [Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning](https://mlsanity.com/paper/2605.23315/) (2026)
- [Characterizing Universal Object Representations Across Vision Models](https://mlsanity.com/paper/2605.13675/) (2026)
- [Language Models Represent and Transform Concepts with Shared Geometry](https://mlsanity.com/paper/2607.04525/) (2026)
- [Better Together: Evaluating the Complementarity of Earth Embedding Models](https://mlsanity.com/paper/2605.18667/) (2026)
- [Representation Alignment Rests on Linear Structure](https://mlsanity.com/paper/2605.28870/) (2026)
- [A Unifying Framework for Concept-Based Representational Similarity](https://mlsanity.com/paper/2606.09653/) (2026)
- [Convergent Emergence of In-Context Learning Across Modalities](https://mlsanity.com/paper/2609.14011/) (2026)
- [What Converges in the Platonic Representation Hypothesis? Structure over Geometry](https://mlsanity.com/paper/2609.27252/) (2026)
- [Deep Learning for BioImaging: What Are We Really Learning?](https://mlsanity.com/paper/2603.13377/) (2026)
- [Similarity of Neural Network Representations in Superposition](https://mlsanity.com/paper/2604.00208/) (2026)
- [Task Ecologies and the Evolution of World-Tracking Representations in Large Language Models](https://mlsanity.com/paper/2604.05469/) (2026)
- [Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering](https://mlsanity.com/paper/2604.16487/) (2026)
- [The Umwelt Representation Hypothesis: Rethinking Universality](https://mlsanity.com/paper/2604.17960/) (2026)
- [Capability neq Interpretability: Human Interpretability of Vision Foundation Models](https://mlsanity.com/paper/2605.20337/) (2026)
- [Signal-to-Noise Ratio and Sample Size Govern Representational Alignment in Neural Networks](https://mlsanity.com/paper/2605.26973/) (2026)
- [PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps](https://mlsanity.com/paper/2606.01788/) (2026)
- [The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders](https://mlsanity.com/paper/2606.07882/) (2026)
- [Order Is Not Control: Driven-Dissipative Response Laws Across Artificial and Biological Systems](https://mlsanity.com/paper/2606.12923/) (2026)
- [Mind the Heads: Topological Representation Alignment for Multimodal LLMs](https://mlsanity.com/paper/2606.23885/) (2026)
- [The Concept of Representation in ML: Beyond Plato and Aristotle](https://mlsanity.com/paper/2607.17800/) (2026)
- [Semantic Networks as Clues: A Theoretical Foundation and Process Optimization for Semantic Network Construction](https://mlsanity.com/paper/2608.01936/) (2026)
- [Learning Deep Modality-Shared Self-Expressiveness for Image Clustering with Textual Information](https://mlsanity.com/paper/2608.08418/) (2026)
- [Mapping and Measuring the Behavioral Evolution of Large Language Models](https://mlsanity.com/paper/2608.11027/) (2026)
- [Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities](https://mlsanity.com/paper/2608.18090/) (2026)
- [Approximate Homomorphisms and Convergent Representations in Transducers](https://mlsanity.com/paper/2608.20428/) (2026)
- [Cross-Lingual Alignment Without Joint Training: Do Monolingual Language Models Converge on Universal Representations?](https://mlsanity.com/paper/2608.27115/) (2026)
- [Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision](https://mlsanity.com/paper/2608.27877/) (2026)
- [From Interpretability Methods to Interpretable Models](https://mlsanity.com/paper/2609.05399/) (2026)

## Abstract (arXiv)

The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics used to measure representational similarity are confounded by network scale: increasing model depth or width can systematically inflate representational similarity scores. To correct these effects, we introduce a permutation-based null-calibration framework that transforms any representational similarity metric into a calibrated score with statistical guarantees. We revisit the Platonic Representation Hypothesis with our calibration framework, which reveals a nuanced picture: the apparent convergence reported by global spectral measures largely disappears after calibration, while local neighborhood similarity, but not local distances, retains significant agreement across different modalities. Based on these findings, we propose the Aristotelian Representation Hypothesis: representations in neural networks are converging to shared local neighborhood relationships.