fidelity

[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions

Code base for the precision, recall, density, and coverage metrics for generative models. ICML 2020.

UI regression and fidelity testing framework

Visual Information Fidelity Code - Python

Official implementation of the Fréchet Radiomic Distance

Counterfactual Local Explanations of AI systems

Autocurator is a comprehensive benchmarking toolkit for evaluating synthetic tabular data. It measures fidelity, coverage, privacy, and utility through quantitative metrics, visual reports, and PCA/correlation diagnostics. Ideal for validating VAE, GAN, Copula, or Diffusion-generated datasets.

A narrative and technical exploration of data authenticity through the four pillars of synthetic data realism, Fidelity, Coverage, Privacy, and Utility. This thought-leadership piece combines storytelling, mathematics, and code to explain how these metrics define the ethical and functional “soul” of data in AI systems.

JavaScript Aware Web Archive Crawler (JAWA) (OSDI'22)

Fidelity cards & Barcode manager for keepass2android

a robust metric (robust fidelity) for XGNN (ICLR24)

Migrated to https://github.com/helcel-net/keepass-fidelity

MTLX Fidelity: MaterialX renderer fidelity testing (MaterialXView, Three.js, Blender). Part of the mtlx suite: https://mtlx.ai

THIS REPO IS NO LONGER MAINTAINED: A fast and simple Promise/A+ implementation

Self-hosted portfolio analytics for self-directed Fidelity investors. Compare your returns to a passive benchmark, adjusted for risk, drawdowns, concentration, and style factors.

Fidelity support for bankroll

Ein Java-Client für FFB-Depots. Features: Stammdaten und Depotbestände abholen, Depotperformance ermitteln.

Turn a Claude Code session into a self-contained HTML/text/Markdown/LaTeX/PDF document — with a fidelity report proving nothing was silently dropped.

蒸馏工厂：把书籍/长视频/播客/访谈/人物素材蒸馏成可执行、可验证、可追溯的 Agent Skills。contract-first + FIDELITY 双 Agent 出厂质检 + 跨模型异族复评（DeepSeek，组织独立台账可查）。五道机器门禁不过不发版；82 个自身缺陷公开登记，数字由测试强制相等。零第三方依赖，默认离线。

MathVet: independent, pre-referee fidelity reviews of AI-generated Lean formalizations. First review: openai/math (235 families). Does the Lean statement say what the paper claims?