Benchmark Contamination From Within: Probe Leak Budgets

Sat, 31 Oct 2026 09:00:00 +0800

A leak budget limits how much the evaluator tells the agent about the held-out data

Key Takeaways

Benchmark contamination has two routes: evaluation items in the training corpus, and adaptive feedback from a held-out evaluator. The second route works on a pristine dataset, and a self-training agent opens it from inside its own episode.
Adaptive data analysis bounds the damage by the information the evaluator discloses. Dwork et al. show that a holdout survives many adaptive queries only when answers are coarsened or noised, and Russo and Zou bound the bias of a data-dependent choice by its mutual information with the data.
The materials adsorption task in NSL Workbench, our open framework, implements that bound literally: the probe tool returns one of 20 percentile bins against a frozen chance reference, at most 3 probes per episode, under a 16-bit budget checked at import time and on every call.
A budget on disclosure is not a theorem about generalisation. Labels stay host-side, the compute sidecar has no network and sees only aliased, label-free exports, every probe is logged, and admission is scored on data the probes never touched.

TL;DR

Most discussion of benchmark contamination is about test items leaking into pretraining corpora, which is why static coding benchmarks are being retired. A second route needs no leak at all: an agent that can query a validation oracle during an episode, and is then trained on the episodes that scored well, overfits the holdout through the feedback channel, exactly as adaptive data analysis predicts. NSL Workbench caps that channel with a per-episode leak budget in bits, quantised percentile bins, a hard call limit, label-free sandboxes and a frozen reference, so the admission score stays an estimate of generalisation rather than of probing skill.

Adaptive Data Analysis on Eigenform Continuous Learning Tool Tips

Benchmark Contamination From Within: Probe Leak Budgets

Key Takeaways

TL;DR