TRUST is a decentralized AI auditing framework that decomposes reasoning into HDAGs, maps agent interactions via the DAAN protocol to CIGs, and uses stake-weighted multi-tier consensus to achieve 72.4% accuracy while proving a Safety-Profitability Theorem that rewards honest auditors.
Judging llm-as-a-judge with mt-bench and chatbot arena
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
LACE enables concurrent reasoning paths in LLMs to interact via lattice attention and a synthetic training pipeline, raising accuracy more than 7 points over independent parallel search.
citing papers explorer
-
TRUST: A Framework for Decentralized AI Service v.0.1
TRUST is a decentralized AI auditing framework that decomposes reasoning into HDAGs, maps agent interactions via the DAAN protocol to CIGs, and uses stake-weighted multi-tier consensus to achieve 72.4% accuracy while proving a Safety-Profitability Theorem that rewards honest auditors.
-
LACE: Lattice Attention for Cross-thread Exploration
LACE enables concurrent reasoning paths in LLMs to interact via lattice attention and a synthetic training pipeline, raising accuracy more than 7 points over independent parallel search.
- SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding