Architecture Modification / Research · Jupyter Notebook

qsbc

Quantized Semantic Bottleneck Classifier (QSBC)

Jarad Peckenpaugh@jpeckenpaugh · Atlas 69.9 · #4= builder

View on GitHub Open Jarad Peckenpaugh's Atlas

What it is

The repository provides infrastructure for the Quantized Semantic Bottleneck Classifier (QSBC) architecture applied to the C3PA privacy-policy dataset, including a data pipeline, agent for generating reasoning, web explorer, and ablation experiments to validate the architecture.

Scored from the code at its last scan, 15 Oct 2026. How merit is scored

Where it counts

NLP & LLMs85%
Machine Learning75%
Data Science50%
AI Agents40%
MLOps20%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the NLP & LLMs board

Whole board

RankProjectBuilderFieldMerit

24GWIQ-atlasAI Developer Tool · PythonGWIQ-atlas is a toolkit for building per-layer activation atlases of language models to enable informed quantization and surgical analysis. It provides tools for activation census, layer analysis, compliance behavior mapping, and atlas construction, but lacks the surgery tools…56.0/100ImplementationRickNLP & LLMs
25apexLibrary / Framework · RustThe repository provides the reference Rust implementation of the APEX (Agent Planning & Execution Specification) DSL, including a parser, validator, interpreter, and tool registry for controlling LLM reasoning and agent workflows.54.8/100ImplementationLuiz Cesar SpiesNLP & LLMs
26qsbcArchitecture Modification / Research · Jupyter Notebook54.1/100ImplementationJarad PeckenpaughNLP & LLMs
27doc-assistant-hfML Application · Jupyter NotebookThe repository provides a document intelligence notebook that fine-tunes a BART summarizer with QLoRA, runs extractive QA using a Longformer model with custom span decoding, and implements a TextRank-based extractive summarizer, all wrapped in a Gradio interface.53.7/100ImplementationPop AlexandruNLP & LLMs
28promptlintAI Developer Tool · Pythonpromptlint is a static analysis linter for LLM prompts that detects common anti-patterns such as prompt injection risks, missing token limits, and hardcoded secrets.53.6/100ImplementationPop AlexandruNLP & LLMs

What it is

Where it counts

Around it on the NLP & LLMs board

More from Jarad Peckenpaugh