Introduces token-sensitive enclosure semantics where each measurement carries an interval and an observation token, defining warranted enclosures as sets of consistent values, with proofs that token-erased summaries cannot recover correct rewrite classes, all mechanized in Lean 4.
A survey on provenance: What for? What form? What from?
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
HKVM-RAG uses key-value-separated hypergraphs to organize LLM evidence tuples into answer-path hyperedges, yielding F1 gains over KG-PPR on two multi-hop QA benchmarks and further gains when combined with dense retrievers.
citing papers explorer
-
Token-Sensitive Enclosure Semantics for Measurement-Bearing Expressions
Introduces token-sensitive enclosure semantics where each measurement carries an interval and an observation token, defining warranted enclosures as sets of consistent values, with proofs that token-erased summaries cannot recover correct rewrite classes, all mechanized in Lean 4.
-
HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG
HKVM-RAG uses key-value-separated hypergraphs to organize LLM evidence tuples into answer-path hyperedges, yielding F1 gains over KG-PPR on two multi-hop QA benchmarks and further gains when combined with dense retrievers.