projects

High-precision sentence boundary detection for legal text

Domain-specific BPE tokenizers for legal, financial, and governmental text, achieving 9-17% efficiency improvements over GPT-4 and LLaMA3

Natural language processing and information extraction for legal and regulatory text

Windows driver vulnerability detection through symbolic execution and taint analysis

Open source Python client for SEC EDGAR data access and analysis

Character-based text boundary detection for legal documents using Random Forest classifiers, achieving balanced precision-recall with F1 score of 0.782

Open-source platform using AI and NLP to make US federal legislation accessible through plain language summaries, ELI5 explanations, and readability metrics

High-performance data preprocessing library for large language model training, supporting pretraining, SFT, and DPO datasets with Rust-powered efficiency

Python library for generating synthetic legal data using the FOLIO knowledge graph, supporting both procedural templates and LLM-based generation

Public RESTful API for the Federated Open Legal Information Ontology, providing programmatic access to 18,000+ legal concepts with multiple output formats

Python library for interacting with the Federated Open Legal Information Ontology, providing search, exploration, and format conversion capabilities

Training data contamination detection library for black-box language models, implementing six testing methods to identify potential data leakage

Python library for Random Forest-based correlation measures, providing alternative approaches to traditional correlation analysis using tree-based ensemble methods

Python 3 library for accessing and analyzing NOAA Global Historical Climatology Network (GHCN) weather and climate data

Python 3 client for the Archive of Many Outdoor Scenes (AMOS), enabling access to billions of outdoor webcam images for computer vision and environmental research

Course materials for "Computer Modeling of Complex Systems" at University of Michigan, teaching agent-based modeling and computational approaches to complex systems

First iteration of "Computer Modeling of Complex Systems" course at University of Michigan, establishing foundation for computational complex systems education

A computational legal research project analyzing Supreme Court decisions and legal precedents using natural language processing

modular ai agent configuration system that eliminates repeated instructions and ensures consistent behavior across coding sessions

python package exploration for ai agents that stops them from hallucinating apis

command interceptors that teach ai agents and developers about modern python tooling

MySQL vulnerability exploit demonstrating default configuration flaws in 2002

University of Michigan bus tracking system running on original Google Maps from a dorm room server

Python statistics library built on numarray in the pre-NumPy and SciPy era

PHP 4.x port of the Java Matrix package for linear algebra computations

PHP 3.x/4.x library for serialization and deserialization between MySQL/PostgreSQL and XML

Web-based personal organization suite predating Google Calendar and Trello by several years

Copyright-clean training resources for large language models

Large-scale copyright-clean dataset containing 132M+ documents and trillions of tokens for training legal language models

A comprehensive 15-year study examining how Supreme Court decisions impact stock market returns, finding significant abnormal returns in 37% of cases

Open-source legal data standard containing 18,000+ standardized legal concepts with multilingual support for improved legal industry interoperability

Original source code and data infrastructure that powered the initial version of usbills.ai platform

Large-scale empirical analysis of regulatory complexity using 165,000+ SEC filings to map the evolution of the U.S. regulatory landscape

An innovative analysis of European financial integration using eigendecomposition of sovereign bond yield correlations from 1872 to 2010

Computational analysis measuring the complexity of the United States Code using mathematical and network science approaches

A machine learning model that predicts Supreme Court voting behavior with 70% accuracy, analyzing 60 years of decisions from 1953-2013

An enhanced Supreme Court prediction model achieving 70.2% accuracy across 200 years of decisions (1816-2015), analyzing over 240,000 justice votes

Comprehensive research examining toxicity and bias in legal language models, demonstrating KL3M's superior safety profile through rigorous testing

Research presenting NUPunkt and CharBoundary libraries for high-precision sentence segmentation in legal text, achieving 29-32% improvement over general-purpose tools

Training transformer models to memorize Linux kernel source code to demonstrate issues with AI training data licensing

Research and development repository for advancing the Kelvin Legal Large Language Model family with new architectures and training approaches

Generating and publishing obvious inventions using AI to challenge the patent system

Research demonstrating GPT-4's ability to pass the Uniform Bar Examination, significantly outperforming both human test-takers and prior AI models

Research evaluating GPT models' capabilities on the Uniform CPA Examination, exploring AI's potential to transform knowledge work

Initial repository for research evaluating GPT models on the CPA exam, later developed into the comprehensive "GPT as Knowledge Worker" project

Groundbreaking research demonstrating GPT-3.5's performance on the Multistate Bar Examination, predicting AI's ability to pass professional legal licensing exams

A humorous AI project that generates absurd "F*** My Life" stories using modern language models, comparing current capabilities to 2013 n-gram approaches