A local CLI for logging predictions before the outcome and checking whether your "80% sure" comes true 80% of the time.
Runs ~20 options strategies against live market data in shadow mode, records every hypothetical fill under worst/base/optimistic assumptions, and grades each with anytime-valid e-processes. Places no orders.
Repository for the paper "Auditing Pay-Per-Token in Large Language Models", AISTATS'26
This repository contains the code for the paper "Optimizing Social Utility in Sequential Experiments".
Measure your agent harness, find where it wastes the model, and prove the fix worked. Harness-agnostic, agent-agnostic, zero dependencies. Reference implementation of HTP-1.
A kernel-userland protocol enforcing information-theoretic bounds on AI adaptivity leakage, benchmark gaming, and capability spillover.
Certified pairwise leaderboards for retrieval evaluation. WITNESS samples a few fresh human labels at known probabilities and uses official qrels and LLM judges only as variance-reducing predictors: unbiased for any judgment source, false-discovery-rate controlled, with label-budget forecasts. One-command reproduction.
Real-time cross-chain bridge exploit detection that accuses only with proof. Caught 422/422 attack payouts across Nomad, Ronin and practice attacks with 0 honest payouts accused. Conservation ledger, e-value false-alarm control, Hawkes contagion radar, signers recovered with ecrecover. CSB-01
Publicly verifiable proof that an LLM endpoint actually spent the compute you paid for — zero provider cooperation. Closes the effort gap (Hollow-LLM) and the transferability gap (IRIS).
Benchmark for statistically valid AI scientist systems, using audit-closed protocols, transparency logs, and sequential inference to prevent false discoveries in autonomous research agents.
Research implementation of anytime-valid group-invariance tests with kernel, adaptive Gaussian, and neural statistics.
Anonymous code and result release for block-calibrated false-discovery control in open-vocabulary detection
Windows instrument for fine-tuning runs: every sample drawn, a report that leads with its answer, and a local-model workbench that builds formula tools and tests what each knob does, with e-value evidence across folders.
Codebase of Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models, accepted at NeurIPS2025
Anytime valid inference in Python: confidence sequences, sequential tests and e-values
MSc thesis: designing e-value evidence around a decision-maker's loss, with an application to Polymarket prices for the 2026 World Cup final.
Label-free drift attribution (model / noise / world / annotator) with anytime-valid guarantees and a frozen pre-registration — closes the zero-label misattribution gap 0.50→0.00 on the recoverable cause; negatives reported as measured boundaries.
Reproducibility artifact for The Price of Peeking: Anytime-Valid Leakage Detection on ML-KEM EM Traces.
Code and data for the letter "Anytime-Valid Alarms for BGP Incident Detection via Conformal e-CUSUM Monitors": online conformal p-values and betting-based e-CUSUM monitors for BGP incident alarms, with seven incidents, ordinary-day baselines and a one-command reproduction.
Statistically valid gates for non-deterministic eval suites. Stop early without losing error control.
To associate your repository with the e-values topic, visit your repo's landing page and select "manage topics."