2026/01/01 by Koichi Takahashi, Yusuke Hayashi
Computer Science · Mathematics · #Benchmark (surveying) #Closure (psychology) #Decoupling (probability) #Empirical research #Latent variable #Physical system #Table (database) #Variable (mathematics) #cs.AI #cs.IT #cs.LG #math.IT
paper · pdf · doi:10.1007/978-3-032-33195-3_24
published in Lecture notes in computer science, 339-354 (Springer Science+Business Media)
openalex publication_date 2026/01/01 · openalex created_date 2026/07/23 · openalex updated_date 2026/07/31
Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption. To connect intelligence to physical efficiency, we propose two complementary bits-per-joule metrics under explicit accounting conventions: (1) Thermodynamic Epiplexity per Joule, new bits of structure about a specified environment-instance variable encoded in an agent's state per unit energy, and (2) Empowerment per Joule, sensorimotor channel capacity per expected energetic cost over a fixed horizon. These give two axes of physical intelligence, recognition versus control, but the resulting numbers are benchmark-relative rather than universal. Drawing on stochastic thermodynamics, we formulate a Landauer-scale closed-cycle benchmark for epiplexity acquisition by combining a thermodynamic-learning inequality with data processing, and clarify why boundary closure is required; conversely, a decoupling construction shows that without such assumptions information gain and in-boundary dissipation need not be tightly linked. For empirical settings where the latent structure variable is unavailable, we recommend compute-bounded MDL epiplexity / compression-gain surrogates. Finally, we propose a unified efficiency framework with a minimal checklist of conventions for relative bits-per-joule comparisons, and give a compact language-model reporting example.