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
1,177–1,200 of 1,660 · 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.
quick and dirty canbus h4xing framework
Autonomous desktop intelligence with MCU Ultron persona, mood-aware workspace orchestration, cyber security sentry, and full PC control.
The repository host gives no description.
Tools for the Computer Incident Response Team :computer:
Python implementation of the Packed Executable iDentifier (PEiD)
Automated 3D brain registration with support for multiple species and atlases.
Parse NTLM challenge messages over HTTP and SMB
Free, open-source SEO audits inside OpenAI Codex CLI. Port of claude-seo: 26 skills, 19 specialist roles, technical SEO / schema / GEO / local / ecommerce.
ComfyUI custom node: one-click character reference sheet (character card) generation, auto slice & recomposition for Qwen-Image 2.1
A collection of tools for painting super-resolution images
Spot vulnerabilities in postgres SQL scripts
PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.
A fully-featured recipe manager web application built using Python and the Flask Framework.
Fish Audio Drama 3 text-to-speech on the TensorFold native CUDA engine for DGX Spark (GB10): recipe, engine patches, benchmarks. Built with Fish Audio.
Accurate and efficient spot detection for microscopy data
AI mentor that corrects your written math visually with local harnesses.
Hierarchical Attentive Recurrent Tracking
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
MicroPython Modbus RTU Slave/Master and TCP Server/Slave library
TranslatedBatch ingestion of Douyin authors' works: identifies the author and fetches public works page by page, generates Obsidian notes by topic, and maintains the author directory, index, and logs; driven by an Agent, with CC Connect as an optional integration.
Re-apply type annotations from .pyi stubs to your codebase.
DSP algorithms for chord detection + key estimation
FoBiS.py, Fortran projects Building System