Asymptotic anytime-valid confidence sequences are constructed for nondegenerate and degenerate U-statistics via Hoeffding projections and a new SAGE boundary for quadratic Gaussian chaos, attaining optimal time-uniform rates.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
NeuroState-Bench supplies human-calibrated tasks and probes that measure commitment integrity in LLM agents and shows this measure diverges from ordinary task success.
citing papers explorer
-
Asymptotic Anytime-Valid Inference for U-statistics
Asymptotic anytime-valid confidence sequences are constructed for nondegenerate and degenerate U-statistics via Hoeffding projections and a new SAGE boundary for quadratic Gaussian chaos, attaining optimal time-uniform rates.
-
NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles
NeuroState-Bench supplies human-calibrated tasks and probes that measure commitment integrity in LLM agents and shows this measure diverges from ordinary task success.
- TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design