Skelf Research

AI & ML interests

Independent research lab. Agent infrastructure, evaluation, and the systems under LLMs. Correctness where the code executes. Receipts, not punditry.

Recent Activity

dipankarsarkar  authored a paper 2 days ago

From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving

dipankarsarkar  authored a paper 2 days ago

A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation

dipankarsarkar  authored a paper 2 days ago

Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance

View all activity

Team members 1