DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
- benchmark
- calibration
- decision-making
- evaluation
47,133 repositories indexed
505–528 of 704 · Most stars
DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.
Interpretable bilinear attention network with domain adaptation improves drug-target prediction.
Interactive details-on-demand data visualizations at scale
Tiny ISO-compliant C++ EXIF and XMP parsing library for JPEG.
Mount the InterPlanetary File System as a mapped drive on Windows
A search interface and wayback machine for the UKWA Solr based warc-indexer framework.
Detailed guide for how to get started with beatoraja or BMS in general. -- For example: What is BMS, How do I set it up, Where do I download songs, How does the community work, How does the difficulty system work
[[I'm slow at replying these days, but I hope to get back to answering questions eventually]] Ask me anything!
A library that simplifies error handling for Functional Programming in Java
Arrow-macros provides Clojure-like arrow macros in Common Lisp
Header only library that parses and plans SQL queries at compile time
In the midst of all the tools out there that you can possibly use to keep track of them. Here's a "shovel" that just works to try them all out.
Magento 2 SEO extension will do perfectly for your better SEO. This is a bundle of outstanding features that are auto-active when you install it from Mageplaza without any code modifications. It is also friendly with your store if you need to insert meta keywords and meta descriptions for your product.
LUIS (Love2D UI System) is a flexible graphical user interface (GUI) framework built on top of the Löve2D game framework. LUIS provides developers with the tools to create dynamic, grid-centric, layered user interfaces for games and applications.
Please note that the warc-indexer tool & code is now supported by NetArchiveSuite. The 'warc-indexer' directory and code that exists in this repo is now only for reference. For support and issues of 'warc-indexer', please communicate with NetArchiveSuite.
ENIGMA HALFpipe is a user-friendly software that facilitates reproducible analysis of fMRI data
Flexible, stream-based abstraction for launching processes
Claude Code skill for naming products, SaaS, and brands. Metaphor-driven naming that avoids AI slop.
A port of jellybeans colorscheme for neovim
The repository host gives no description.
🐿️ A metadata-driven Minecraft launcher for reproducible, storage-efficient instances and a built-in CLI with MCP mode for AI agents.
Agent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients.
A strongly-typed genetic programming framework for Python
A dataset of D&D characters submitted to https://oganm.com/shiny/printSheetApp and https://oganm.com/shiny/interactiveSheet. A superset of characters used in oganm/dndstats