Benchmark for statistically valid AI scientist systems, using audit-closed protocols, transparency logs, and sequential inference to prevent false discoveries in autonomous research agents.
-
Updated
Mar 5, 2026 - Python
Benchmark for statistically valid AI scientist systems, using audit-closed protocols, transparency logs, and sequential inference to prevent false discoveries in autonomous research agents.
Fisher Flow: A unified information-geometric framework for sequential inference revealing how modern optimizers (Adam, Natural Gradient, K-FAC, EWC) emerge as special cases of Fisher information propagation
Add a description, image, and links to the sequential-inference topic page so that developers can more easily learn about it.
To associate your repository with the sequential-inference topic, visit your repo's landing page and select "manage topics."