# Falsifying Discriminant Validity of Predictive Algorithms

arXiv: https://arxiv.org/abs/2601.17146 · HTML: https://mlsanity.com/paper/2601.17146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 78 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Builds on (most cited first, 23 of 23)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Estimating means of bounded random variables by betting](https://mlsanity.com/paper/2010.09686/) (2020)
- [Game-theoretic statistics and safe anytime-valid inference](https://mlsanity.com/paper/2210.01948/) (2022)
- [The Frontiers of Fairness in Machine Learning](https://mlsanity.com/paper/1810.08810/) (2018)
- [Problem Formulation and Fairness](https://mlsanity.com/paper/1901.02547/) (2019)
- [It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks](https://mlsanity.com/paper/2106.05498/) (2021)
- [Counterfactual Risk Assessments, Evaluation, and Fairness](https://mlsanity.com/paper/1909.00066/) (2019)
- [Measurement to Meaning: A Validity-Centered Framework for AI Evaluation](https://mlsanity.com/paper/2505.10573/) (2025)
- [A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms](https://mlsanity.com/paper/2206.14983/) (2022)
- [Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making](https://mlsanity.com/paper/2302.06503/) (2023)
- [The Situate AI Guidebook: Co-Designing a Toolkit to Support Multi-Stakeholder Early-stage Deliberations Around Public Sector AI Proposals](https://mlsanity.com/paper/2402.18774/) (2024)
- [The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models](https://mlsanity.com/paper/2510.23191/) (2025)
- [Conditional calibration for false discovery rate control under dependence](https://mlsanity.com/paper/2007.10438/) (2020)
- [Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints](https://mlsanity.com/paper/2306.13738/) (2023)
- [The Misuse of AUC: What High Impact Risk Assessment Gets Wrong](https://mlsanity.com/paper/2305.18159/) (2023)
- [Robust Design and Evaluation of Predictive Algorithms under Unobserved Confounding](https://mlsanity.com/paper/2212.09844/) (2022)
- [The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning](https://mlsanity.com/paper/2410.09600/) (2024)

## Abstract (arXiv)

Empirical investigations into unintended model behavior often show that the algorithm is predicting another outcome than what was intended. These expos'es highlight the need to identify when algorithms predict unintended quantities - ideally before deploying them into consequential settings. We propose a falsification framework that provides a principled statistical test for discriminant validity: the requirement that an algorithm predict intended outcomes better than impermissible ones. Drawing on falsification practices from causal inference, econometrics, and psychometrics, our framework compares calibrated prediction losses across outcomes to assess whether the algorithm exhibits discriminant validity with respect to a specified impermissible proxy. In settings where the target outcome is difficult to observe, multiple permissible proxy outcomes may be available; our framework accommodates both this setting and the case with a single permissible proxy. Throughout we use nonparametric hypothesis testing methods that make minimal assumptions on the data-generating process. We illustrate the method in an admissions setting, where the framework establishes discriminant validity with respect to gender but fails to establish discriminant validity with respect to race. This demonstrates how falsification can serve as an early validity check. We also provide analysis in a criminal justice setting, where we highlight the limitations of our framework and emphasize the need for complementary approaches to assess other aspects of construct validity and external validity.