mlsanityData to 7 Oct 2026

Performance is not enough: the story told by a Rashomon quartet

arXiv 2302.13356 ↗First posted 26 Feb 2023stat.ML cs.LG stat.APcited by 9

Not on the map. Why?

Abstract (arXiv)

The usual goal of supervised learning is to find the best model, the one that optimizes a particular performance measure. However, what if the explanation provided by this model is completely different from another model and different again from another model despite all having similarly good fit statistics? Is it possible that the equally effective models put the spotlight on different relationships in the data? Inspired by Anscombe's quartet, this paper introduces a Rashomon Quartet, i.e. a set of four models built on a synthetic dataset which have practically identical predictive performance. However, the visual exploration reveals distinct explanations of the relations in the data. This illustrative example aims to encourage the use of methods for model visualization to compare predictive models beyond their performance.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 8 of its 25 references that are in the map. First posted on arXiv 26 Feb 2023.

Builds on

8 of 25 references.

References · 8

  1. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  2. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  3. 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 212
  4. 2018DALEX: explainers for complex predictive modelscited by 28
  5. 2020The Grammar of Interactive Explanatory Model Analysiscited by 24
  6. 2021Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Processcited by 24
  7. 2021Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanationscited by 15
  8. 2023Causal quartets: Different ways to attain the same average treatment effectcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 5; 2026: 1.

9 papers.

  1. 2025Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learningcited by 17
  2. 2023Exploration of the Rashomon Set Assists Trustworthy Explanations for Medical Datacited by 11
  3. 2024An Experimental Study on the Rashomon Effect of Balancing Methods in Imbalanced Classificationcited by 11
  4. 2025The Role of Hyperparameters in Predictive Multiplicitycited by 4
  5. 2025Birds look like cars: Adversarial analysis of intrinsically interpretable deep learningcited by 3
  6. 2024Rashomon effect in Educational Research: Why More is Better Than One for Measuring the Importance of the Variables?cited by 1
  7. 2025Towards the Formalization of a Trustworthy AI for Mining Interpretable Models explOiting Sophisticated Algorithmscited by 1
  8. 2025VAR: Visual Analysis for Rashomon Set of Machine Learning Models' Performancecited by 0
  9. 2026Analyzing the Temporal Factors for Anxiety and Depression Symptoms with the Rashomon Perspectivecited by 0