measurement-validity

Here are 4 public repositories matching this topic...

Nasser-Lim / jamo-bench

JAMO — OCR-mediated Hangul rendering benchmark. Code companion to huggingface.co/datasets/Nasser4963/jamo-gold

benchmark ocr hangul text-to-image zenodo korean-nlp glyph-rendering evaluation-methodology ai-benchmarking measurement-validity

Updated Aug 17, 2026
Python

Pranavsingh431 / Perturbation-Based-Measurements

Star

Code, data, and raw model outputs for "Failure Modes in Perturbation-Based Measurement of Language Model Reliability". evaluation/reproduce.py re-derives every reported number offline, no API key required.

benchmark language-models reproducibility uncertainty-quantification llm-evaluation sycophancy research-artifact measurement-validity

Updated Aug 1, 2026
Python

KvashaIhor / state-management-benchmark

Star

A controlled benchmark of eight React state management configurations, with the full replication package: cross-hardware, cross-engine, and a row sweep from 10 to 1000 rows.