# Is your model predicting the past?

arXiv: https://arxiv.org/abs/2206.11673 · HTML: https://mlsanity.com/paper/2206.11673/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 23 Jun 2022.

## Builds on (most cited first, 17 of 17)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Delayed Impact of Fair Machine Learning](https://mlsanity.com/paper/1803.04383/) (2018)
- [Outcome Indistinguishability](https://mlsanity.com/paper/2011.13426/) (2020)
- [Robustness to Spurious Correlations via Human Annotations](https://mlsanity.com/paper/2007.06661/) (2020)
- [It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks](https://mlsanity.com/paper/2106.05498/) (2021)
- [The age of secrecy and unfairness in recidivism prediction](https://mlsanity.com/paper/1811.00731/) (2018)
- [Low-Degree Multicalibration](https://mlsanity.com/paper/2203.01255/) (2022)
- [In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction](https://mlsanity.com/paper/2005.04176/) (2020)
- [ProPublica's COMPAS Data Revisited](https://mlsanity.com/paper/1906.04711/) (2019)

## Built on by (most cited first, 5 of 5)

- [Difficult Lessons on Social Prediction from Wisconsin Public Schools](https://mlsanity.com/paper/2304.06205/) (2023)
- [Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making](https://mlsanity.com/paper/2302.06503/) (2023)
- [Allocation Requires Prediction Only if Inequality Is Low](https://mlsanity.com/paper/2406.13882/) (2024)
- [The Hidden Cost of Waiting for Accurate Predictions](https://mlsanity.com/paper/2503.00650/) (2025)
- [Invariant Causal Set Covering Machines](https://mlsanity.com/paper/2306.04777/) (2023)

## Abstract (arXiv)

When does a machine learning model predict the future of individuals and when does it recite patterns that predate the individuals? In this work, we propose a distinction between these two pathways of prediction, supported by theoretical, empirical, and normative arguments. At the center of our proposal is a family of simple and efficient statistical tests, called backward baselines, that demonstrate if, and to what extent, a model recounts the past. Our statistical theory provides guidance for interpreting backward baselines, establishing equivalences between different baselines and familiar statistical concepts. Concretely, we derive a meaningful backward baseline for auditing a prediction system as a black box, given only background variables and the system's predictions. Empirically, we evaluate the framework on different prediction tasks derived from longitudinal panel surveys, demonstrating the ease and effectiveness of incorporating backward baselines into the practice of machine learning.