You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
LAWLIA is an open-source computational legal framework designed to revolutionize legal reasoning and analysis. It combines the power of large language models with a structured syntactical grammar to facilitate precise legal assessments, truth values, and verdicts. LAWLIA is the future of computational jurisprudence
LawVM compiles human-written amendment acts into auditable point-in-time legal text-state. It treats legislation as executable state transitions, preserving provenance, replay evidence, and divergence findings across jurisdictions.
ProPublica’s claim about racial bias in COMPAS can be largely attributed to the bias of the Broward County dataset that they used for analysis, instead of COMPAS itself.
188 DIFC/ADGM/SICC judgments scored under a two-grader-type protocol (39 LLM + 149 regex; provenance per entry). 12 Catala rule modules, 7 case traces, analysis plan with H1-H8 stop rules. Reproducible via Docker.
Read Matcha legal-reasoning code as default logic: a syntax checker, a Reiter/prioritized extension solver with Lean certificates, and a Claude Code skill for neuro-symbolic argument review.