Quipu: A Governed Bitemporal Knowledge Graph Store
Researchers introduce Quipu, a bitemporal knowledge graph store designed to manage the high-velocity, untrusted data writes generated by autonomous AI agents.
- Traditional knowledge graphs lack the governance required for high-speed agentic writes.
- Quipu uses bitemporal logic to manage data, trust labels, and governance rules.
- The system prevents data corruption by evaluating predicates before accepting new facts.
- The architecture is designed to be embeddable for direct integration into agent workflows.
As AI agents become increasingly capable of writing to knowledge graphs, traditional storage methods are proving insufficient. Current systems often rely on human-curated defaults, such as accepting all writes and cleaning data later, which fails under the massive scale and speed of agentic workloads.
Quipu addresses these failures by inverting standard storage defaults. It introduces a system where no fact is accepted without passing through a gate that evaluates the pending state. This ensures that data integrity is maintained even when multiple agents are contributing simultaneously.
By utilizing bitemporal logic, Quipu tracks both when a fact was true in the real world and when it was recorded in the database. This allows for complex auditing and versioning of trust labels, verdicts, and the governance rules themselves, providing a robust foundation for reliable agentic memory.
Provides a new architectural pattern for building reliable agentic memory systems.
Ensures AI agents can contribute to databases without corrupting factual integrity.
- bitemporal
- A data model that tracks two distinct timelines: when an event occurred and when it was recorded.
- knowledge graph
- A programmatic way to represent a network of real-world entities and their interrelationships.
Cloud-Based Artificial Intelligence Classification of Common Intracranial Tumors on Magnetic Resonance Imaging - Cureus
Improving the matrix multiplication exponent with modern optimization and AlphaEvolve
AutoSR: Automatic Symbolic Regression by Searching Research States
Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text
Proteus: Incremental Memory Activation for Long-Context Sequence Modeling
AI vs AI: Can artificial intelligence contain the fake news epidemic that it has helped unleash? - Genetic Literacy Project
Researchers explore whether AI can detect and mitigate fake news, a problem partly fueled by AI itself.
AI and the New Age of Bioweapons - Foreign Affairs
A Foreign Affairs analysis warns that AI could dramatically lower the barrier to creating bioweapons, accelerating proliferation risks.
Artificial Intelligence: Organizations Across the Americas Urge the IACHR to Address the Environmental and Social Impacts of Rapidly Expanding Data Centers - elciudadano.com
Organizations across the Americas have formally requested the Inter-American Commission on Human Rights (IACHR) to investigate the environmental and social consequences of rapidly expanding data centers, driven by artificial intelligence development.
Suburban man allegedly used AI to create child sexual abuse material: Prosecutors - NBC 5 Chicago
A suburban man is accused of using AI to create child sexual abuse material, according to prosecutors.
Appeals court flags AI-generated fake cases in San Antonio ISD lawsuit - KSAT
A federal appeals court in Texas flagged AI-generated fake cases in a lawsuit involving San Antonio ISD, raising concerns about the reliability of AI in legal filings.
BusinessAnthropic’s annualized revenue surges to $65B
Anthropic’s annualized revenue has skyrocketed to $65 billion, adding $18 billion in just two months.