# The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models

arXiv: https://arxiv.org/abs/2510.23191 · HTML: https://mlsanity.com/paper/2510.23191/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 137 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 30 of 47)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [WeatherBench: A benchmark dataset for data-driven weather forecasting](https://mlsanity.com/paper/2002.00469/) (2020)
- [Data and its (dis)contents: A survey of dataset development and use in machine learning research](https://mlsanity.com/paper/2012.05345/) (2020)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models](https://mlsanity.com/paper/2305.14763/) (2023)
- [Can Machines Learn Morality? The Delphi Experiment](https://mlsanity.com/paper/2110.07574/) (2021)
- [The Benchmark Lottery](https://mlsanity.com/paper/2107.07002/) (2021)
- [The Effect of Natural Distribution Shift on Question Answering Models](https://mlsanity.com/paper/2004.14444/) (2020)
- [Reduced, Reused and Recycled: The Life of a Dataset in Machine Learning Research](https://mlsanity.com/paper/2112.01716/) (2021)
- [The Measure and Mismeasure of Fairness](https://mlsanity.com/paper/1808.00023/) (2018)
- [From ImageNet to Image Classification: Contextualizing Progress on Benchmarks](https://mlsanity.com/paper/2005.11295/) (2020)
- [Generalization in Adaptive Data Analysis and Holdout Reuse](https://mlsanity.com/paper/1506.02629/) (2015)
- [The Ladder: A Reliable Leaderboard for Machine Learning Competitions](https://mlsanity.com/paper/1502.04585/) (2015)
- [Cold Case: The Lost MNIST Digits](https://mlsanity.com/paper/1905.10498/) (2019)
- [Measurement to Meaning: A Validity-Centered Framework for AI Evaluation](https://mlsanity.com/paper/2505.10573/) (2025)
- [Targeting the Benchmark: On Methodology in Current Natural Language Processing Research](https://mlsanity.com/paper/2007.04792/) (2020)
- [Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement](https://mlsanity.com/paper/2505.08245/) (2025)
- [Difficult Lessons on Social Prediction from Wisconsin Public Schools](https://mlsanity.com/paper/2304.06205/) (2023)
- [Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks](https://mlsanity.com/paper/2405.01719/) (2024)

## Built on by (most cited first, 13 of 13)

- [QuitoBench: A High-Quality Open Time Series Forecasting Benchmark](https://mlsanity.com/paper/2603.26017/) (2026)
- [Establishing Construct Validity in LLM Capability Benchmarks Requires Nomological Networks](https://mlsanity.com/paper/2603.15121/) (2026)
- [The COTe score: A decomposable framework for evaluating Document Layout Analysis models](https://mlsanity.com/paper/2603.12718/) (2026)
- [How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness](https://mlsanity.com/paper/2605.23628/) (2026)
- [Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation](https://mlsanity.com/paper/2609.04298/) (2026)
- [Falsifying Discriminant Validity of Predictive Algorithms](https://mlsanity.com/paper/2601.17146/) (2026)
- [Questionnaire Responses Do not Capture the Safety of AI Agents](https://mlsanity.com/paper/2603.14417/) (2026)
- [From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World](https://mlsanity.com/paper/2605.10834/) (2026)
- [Validity Threats for Foundation Model Research](https://mlsanity.com/paper/2606.05029/) (2026)
- [Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins](https://mlsanity.com/paper/2607.09306/) (2026)
- [When benchmark inferences do not compose: Projectibility in AI evaluation](https://mlsanity.com/paper/2607.26159/) (2026)
- [Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints](https://mlsanity.com/paper/2609.04198/) (2026)
- [When Evidence Changes the Subject: Subject-Typed Claim Licensing for Learned Routing](https://mlsanity.com/paper/2609.33505/) (2026)

## Abstract (arXiv)

Predictive benchmarking, evaluating machine learning models based on predictive performance and competitive ranking, is central to machine learning research and scientific inquiry. However, benchmark scores at best measure performance relative to a specific dataset and learning problem. Drawing substantial scientific inferences requires additional assumptions. Adapting ideas from psychological validity theory, we propose validity conditions that make these assumptions explicit. In two case studies---ImageNet and the Fragile Families Challenge---we show how benchmark results can support inferences about research progress and limits of predictability, situating predictive benchmarking as a distinct epistemic practice in machine learning.