# Prediction-Powered Active Testing

arXiv: https://arxiv.org/abs/2607.08347 · HTML: https://mlsanity.com/paper/2607.08347/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 82 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [tinyBenchmarks: evaluating LLMs with fewer examples](https://mlsanity.com/paper/2402.14992/) (2024)
- [TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models](https://mlsanity.com/paper/2511.08667/) (2025)
- [PPI++: Efficient Prediction-Powered Inference](https://mlsanity.com/paper/2311.01453/) (2023)
- [On Statistical Bias In Active Learning: How and When To Fix It](https://mlsanity.com/paper/2101.11665/) (2021)
- [Active Statistical Inference](https://mlsanity.com/paper/2403.03208/) (2024)
- [Label-Efficient Model Selection for Text Generation](https://mlsanity.com/paper/2402.07891/) (2024)
- [Scaling Up Active Testing to Large Language Models](https://mlsanity.com/paper/2508.09093/) (2025)
- [Active Measurement: Efficient Estimation at Scale](https://mlsanity.com/paper/2507.01372/) (2025)
- [Sample Efficient Model Evaluation](https://mlsanity.com/paper/2109.12043/) (2021)
- [SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion](https://mlsanity.com/paper/2511.04854/) (2025)
- [Revisiting Active Sequential Prediction-Powered Mean Estimation](https://mlsanity.com/paper/2604.18569/) (2026)

## Built on by (most cited first, 1 of 1)

- [The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits](https://mlsanity.com/paper/2610.06610/) (2026)

## Abstract (arXiv)

Active testing provides a label--efficient approach to risk estimation by adaptively selecting which test points should be labelled. However, existing estimators fail to exploit the informative predictions of powerful black--box models, even though such predictions are increasingly available in settings where labels remain expensive. To address this, we propose Prediction--Powered Active Testing (PPAT), a novel label--efficient risk estimation framework that combines the unbiased LURE estimator citepfarquhar2021statistical with a prediction--powered control variate. Rather than using proxy predictions as biased pseudo--labels, PPAT uses them to residualise the loss, preserving unbiasedness while reducing variance. Beyond the estimator itself, PPAT also changes which points should be acquired: we derive oracle and practical surrogate--based acquisition rules tailored to reducing the variance of our estimator. Moreover, we establish asymptotic normality for PPAT, yielding asymptotically valid confidence intervals and thus a principled estimate of the uncertainty around our estimates. Across tabular regression and image--classification tasks, PPAT outperforms existing methods in risk estimation, while its confidence intervals attain the target coverage with substantially fewer labels and smaller widths.