Crumb
PulseAugur coverage of Crumb — every cluster mentioning Crumb across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
AutoIndex learns document representation programs to boost retrieval performance
Researchers have introduced AutoIndex, a novel framework designed to learn executable transformations for document representation. This system optimizes document preprocessing before indexing, moving beyond traditional …
-
New system Crumb ensures human accountability for AI agent actions
A new system called Crumb has been developed to address the challenge of attributing AI agent actions to specific human users, a requirement mandated by the EU AI Act. Current logging practices often only record the age…
-
Identity verification systems must fetch keys dynamically, not pin static ones
The author discusses a challenge in verifying digital identity tokens, specifically when the signing keys of identity providers (IdPs) are rotated. Initially, the author manually pinned static public keys, but this appr…
-
AI agent identity tracking across companies solved with token stapling
An AI agent acting on behalf of a human user can obscure the user's identity when interacting with systems across different companies. Standard token exchange protocols often drop the original authentication proof when …
-
Crumb system preserves human audit trails across company AI agent interactions
A new method called Crumb has been developed to address the challenge of tracking human accountability for actions taken by AI agents across different companies. Current systems struggle to maintain a clear audit trail …
-
New system Crumb logs human accountability for AI agent actions
A new system called Crumb has been developed to address the challenge of attributing actions taken by AI agents to specific human users, a requirement mandated by regulations like the EU AI Act. Current logging practice…
-
CRUMB improves PFN inference efficiency with context batching
Researchers have developed CRUMB, a novel inference wrapper designed to improve the efficiency of prior-fitted networks (PFNs). PFNs are powerful tabular foundation models that can perform in-context learning, but their…