Skip to content
View joshuadefreitas's full-sized avatar
💭
Swamped
💭
Swamped

Block or report joshuadefreitas

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
joshuadefreitas/README.md

Joshua de Freitas

I'm an engineer. I like building things, asking how they work, and trying to understand systems before I have a neat answer for them.

Most of what I make starts as a question, a small experiment, or a tool I wish existed.

I'm currently working on Sekiya, an independent place for computer science and computational experiments.

When I'm not working, I enjoy the vibrance of Madrid. Made in Rotterdam.

Website · LinkedIn

Pinned Loading

  1. SekiyaLab/deep-lob SekiyaLab/deep-lob Public

    A PyTorch pipeline for learning short-horizon price movement from synthetic limit order book data.

    Python 2

  2. trace-npm trace-npm Public

    See what an npm lifecycle script actually did: files touched, processes spawned, network endpoints contacted. Linux + strace.

    JavaScript

  3. neural-field-study neural-field-study Public

    A deterministic computational neuroscience field study.

    JavaScript 1

  4. SekiyaLab/clock-dataset SekiyaLab/clock-dataset Public

    Point-in-time vs latest-data reconstruction: measuring hindsight bias in revision-aware historical decisions.

    Python

  5. SekiyaLab/decision-assurance SekiyaLab/decision-assurance Public

    Calibrated finite-capacity decision assurance under predictive uncertainty.

    Python

  6. SekiyaLab/degradation-diagnosis SekiyaLab/degradation-diagnosis Public

    Detection versus diagnosis of model degradation with label-free estimation and explicit ambiguity.

    Python