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
697–720 of 942 · 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.
Graph to sequence implemented in Pytorch combining Graph convolutional networks and opennmt-py
Reverse engineering tool for virtualization wrappers
lua code export save to be run on seedsow switch demo exploit
Generate Keyboard Walk Dictionaries for cracking
PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.
Sample skills, scripts, and reference workflows for AI-assisted planning, setup, and configuration of Oracle Fusion Cloud Applications.
AI mentor that corrects your written math visually with local harnesses.
Previews for headless Wagtail setups
This repository is a proof of concept toolbox for using Deep Belief Nets for Topic Modeling in Python.
FoBiS.py, Fortran projects Building System
Investor’s Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
2 character sheets + 1 line of story → a finished AI anime episode. Agent skill for Claude Code / Codex, powered by Renoise MCP.
🔫 Python package for interacting with CS:GO Game Coordinator
Auto-QChem is an automated workflow for the generation and storage of DFT calculations for organic molecules.
Local-only browser fingerprint & identity rotation toolkit for authorized security testing. Tor/obfs4, coherent profiles, WebRTC/DNS leak protection.
Inner ear models for Python
Mock an SSH server and define all commands it supports (Python, Twisted)
A sklearn-compatible Python implementation of Multifactor Dimensionality Reduction (MDR) for feature construction.
Automated line item generator for Prebid.js and Google Ad Manager
Produce watertight polygonal vector maps by tracing raster images
Translated麦卡收藏家 (Maika Collector, "McCard Collector") · A card collection Skill + web version based on McDonald's China MCP (entry for the McDonald's Programmer Creative Development Contest)
Decorator which checks whether the function is called with the correct type of parameters.
The OTX Suricata Rule Generator can be used to create the rules and configuration for Suricata to alert on indicators from your OTX account.