Skip to content
View ACNoonan's full-sized avatar
18 followers · 13 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx3Achievement: YOLOAchievement: QuickdrawAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx3Achievement: YOLOAchievement: QuickdrawAchievement: Arctic Code Vault Contributor

Block or report ACNoonan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ACNoonan/README.md

Adam Noonan

I work on calibrated uncertainty: when a model says 85%, does 85% happen?

Research

The Exceedance Design Effect · code and Lean proofs
A dataset does not have one effective sample size. In our document experiment, the same 1,000 rows carried about 217 independent observations' worth of information at the median, and about 621 at the 95th percentile. The number of rows is a property of the dataset. The effective sample size belongs to the analysis.

SureStop · pip install surestop
Stop bad training runs early, with a conformal bound on how often you stop a good one. Measured on 400 LoRA fine-tuning runs under a pre-registered protocol. Ships as an Optuna pruner in OptunaHub.

LOVE / AIGVE-60K reproduction
Independent reproduction of an ICML 2026 paper. 5 of 6 claims reproduced on one A100.

Soothsayer
You pick the coverage level, and the oracle returns the price band that empirically delivers it. Validated on 12 years of weekend gaps across 10 tickers.

Systems

  • scryer · Rust data platform that writes versioned, deduplicated Parquet for market research.
  • solana-dlmm-meteora · Pure-Rust swap math for Meteora's DLMM, with no RPC.
  • restate-elixir · Elixir SDK for Restate. Passes all 202 official conformance tests.

Director of Data & AI at Digital Locke · adamnoonan.xyz · ORCID · LinkedIn

Pinned Loading

  1. exceedance-design-effect exceedance-design-effect Public

    A dataset has no single effective sample size: it depends on the question you ask. Lean proofs, analysis scripts and the neff estimator for my paper, The Exceedance Design Effect (arXiv:2608.21262,…

    Python 1

  2. soothsayer soothsayer Public

    Calibration-transparent fair-value oracle for tokenized RWAs on Solana — pick coverage τ, get the band that empirically delivers it plus a receipt re-derivable from public data. Deployed M6 LWC: he…

    Python 4

  3. surestop surestop Public

    Stop bad runs early, with a conformal bound on how often you stop a good one

    Python 2

  4. scryer scryer Public

    Manifest-driven Rust data platform for crypto, oracle, and market-data fetches, writing versioned deduped parquet for quantitative research.

    Rust 3

  5. solana-dlmm-meteora solana-dlmm-meteora Public

    Pure-Rust, no-RPC swap math for the Meteora DLMM (bin-based AMM) on Solana — dynamic-fee FSM, limit orders, exact-in/exact-out orchestrators. Extracted byte-for-byte from MeteoraAg/dlmm-sdk with no…

    Rust 6 1

  6. love-repro-aigve60k love-repro-aigve60k Public

    Independent reproduction of LOVE / AIGVE-60K (ICML 2026 #1055). 5/6 claims reproduced on 1x A100; perceptual quality to ΔSRCC 0.0002.

    Shell 1