We are committed to research that makes AI systems more durable, inspectable, and useful across the full arc of real work. These papers ground the product work behind ThruWire: explicit lineage, durable intermediate artifacts, and shared structures that humans and agents can improve over time.
Josh Rosen and Seth Rosen · Submitted May 7, 2026
Introduces execution lineage: representing AI-native work as a directed acyclic graph of artifact-producing computations with explicit dependencies, stable intermediate boundaries, and identity-based replay.
Artificial Intelligence, Multiagent Systems, Software Engineering
Josh Rosen and Seth Rosen · Submitted May 12, 2026
Formalizes durable intermediate artifacts as typed, structured, addressable, versioned, dependency-aware work products that humans and agents can inspect, revise, supersede, and improve.
Artificial Intelligence, Multiagent Systems