3 papers
cs.IT2026
The Derivation Penalty in Premise-Erasure Caching: Capacity, Strong Converse, and Dispersion Dichotomy
Jianfeng Xu
We introduce an information-theoretic framework for caching in derivation-based reasoning engines under independent premise erasure. Two decoder models are compared: a coded scheme…
cs.IT2026
Derivation Depth as an Information Metric: Axioms, Coding Theorems, and Storage--Computation Tradeoffs
Jianfeng Xu
We introduce derivation depth-a computable metric of the reasoning effort needed to answer a query based on a given set of premises. We model information as a two-layered structure…
cs.IT2025
Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints
Jianfeng Xu, Zeyan Li
The rapid scaling of artificial intelligence models has revealed a fundamental tension between model capacity (storage) and inference efficiency (computation). While classical info…