Repository for the paper "Auditing Pay-Per-Token in Large Language Models", AISTATS'26
-
Updated
Mar 23, 2026 - Jupyter Notebook
#
e-values
Here are 4 public repositories matching this topic...
A kernel-userland protocol enforcing information-theoretic bounds on AI adaptivity leakage, benchmark gaming, and capability spillover.
rust cryptography kernel webassembly wasm verification sandboxing formal-methods systems-programming ai-safety differential-privacy reference-monitor e-values agentic-ai deterministic-execution ai-safety-research epistemic-security benchmark-integrity
-
Updated
Mar 5, 2026 - Rust
This repository contains the code for the paper "Optimizing Social Utility in Sequential Experiments".
decision-making game-theory bayesian markov-decision-processes hypothesis-testing antibiotics subsidies bayesian-game social-welfare e-values strategic-behavior stackelberg-games
-
Updated
Apr 22, 2026 - Jupyter Notebook
Benchmark for statistically valid AI scientist systems, using audit-closed protocols, transparency logs, and sequential inference to prevent false discoveries in autonomous research agents.
reproducible-science audit-log ai-agents p-hacking scientific-machine-learning scientific-discovery autonomous-research transparency-log statistical-validity e-values self-driving-lab ai-governance automated-science research-automation agentic-ai ai-scientist sequential-inference deterministic-replay e-process optional-stopping
-
Updated
Mar 12, 2026 - Python
Improve this page
Add a description, image, and links to the e-values topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the e-values topic, visit your repo's landing page and select "manage topics."