# Revisiting Rashomon: A Comment on "The Two Cultures"

arXiv: https://arxiv.org/abs/2104.02150 · HTML: https://mlsanity.com/paper/2104.02150/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 5 Apr 2021.

## Builds on (most cited first, 8 of 8)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Predictive Multiplicity in Classification](https://mlsanity.com/paper/1909.06677/) (2019)

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

- [Investigating the Impact of Balancing, Filtering, and Complexity on Predictive Multiplicity: A Data-Centric Perspective](https://mlsanity.com/paper/2412.09712/) (2024)
- [X Hacking: The Threat of Misguided AutoML](https://mlsanity.com/paper/2401.08513/) (2024)

## Abstract (arXiv)

Here, I provide some reflections on Prof. Leo Breiman's "The Two Cultures" paper. I focus specifically on the phenomenon that Breiman dubbed the "Rashomon Effect", describing the situation in which there are many models that satisfy predictive accuracy criteria equally well, but process information in the data in substantially different ways. This phenomenon can make it difficult to draw conclusions or automate decisions based on a model fit to data. I make connections to recent work in the Machine Learning literature that explore the implications of this issue, and note that grappling with it can be a fruitful area of collaboration between the algorithmic and data modeling cultures.