Toward Thermodynamic Reservoir Computing: Exploring SHA-256 ASICs as Potential Physical Substrates
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908747837734912 |
|---|---|
| author | de Lafuente, Francisco Angulo Veselov, Vladimir Goodman, Richard |
| author_facet | de Lafuente, Francisco Angulo Veselov, Vladimir Goodman, Richard |
| contents | We propose a theoretical framework--Holographic Reservoir Computing (HRC)--which hypothesizes that the thermodynamic noise and timing dynamics in voltage-stressed Bitcoin mining ASICs (BM1366) could potentially serve as a physical reservoir computing substrate. We present the CHIMERA (Conscious Hybrid Intelligence via Miner-Embedded Resonance Architecture) system architecture, which treats the SHA-256 hashing pipeline not as an entropy source, but as a deterministic diffusion operator whose timing characteristics under controlled voltage and frequency conditions may exhibit computationally useful dynamics. We report preliminary observations of non-Poissonian variability in inter-arrival time statistics during edge-of-stability operation, which we term the "Silicon Heartbeat" hypothesis. Theoretical analysis based on Hierarchical Number System (HNS) representations suggests that such architectures could achieve O(log n) energy scaling compared to traditional von Neumann O(2^n) dependencies. However, we emphasize that these are theoretical projections requiring experimental validation. We present the implemented measurement infrastructure, acknowledge current limitations, and outline the experimental program necessary to confirm or refute these hypotheses. This work contributes to the emerging field of thermodynamic computing by proposing a novel approach to repurposing obsolete cryptographic hardware for neuromorphic applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01916 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Toward Thermodynamic Reservoir Computing: Exploring SHA-256 ASICs as Potential Physical Substrates de Lafuente, Francisco Angulo Veselov, Vladimir Goodman, Richard Neural and Evolutionary Computing C.1.3; I.2.6; B.7.1 We propose a theoretical framework--Holographic Reservoir Computing (HRC)--which hypothesizes that the thermodynamic noise and timing dynamics in voltage-stressed Bitcoin mining ASICs (BM1366) could potentially serve as a physical reservoir computing substrate. We present the CHIMERA (Conscious Hybrid Intelligence via Miner-Embedded Resonance Architecture) system architecture, which treats the SHA-256 hashing pipeline not as an entropy source, but as a deterministic diffusion operator whose timing characteristics under controlled voltage and frequency conditions may exhibit computationally useful dynamics. We report preliminary observations of non-Poissonian variability in inter-arrival time statistics during edge-of-stability operation, which we term the "Silicon Heartbeat" hypothesis. Theoretical analysis based on Hierarchical Number System (HNS) representations suggests that such architectures could achieve O(log n) energy scaling compared to traditional von Neumann O(2^n) dependencies. However, we emphasize that these are theoretical projections requiring experimental validation. We present the implemented measurement infrastructure, acknowledge current limitations, and outline the experimental program necessary to confirm or refute these hypotheses. This work contributes to the emerging field of thermodynamic computing by proposing a novel approach to repurposing obsolete cryptographic hardware for neuromorphic applications. |
| title | Toward Thermodynamic Reservoir Computing: Exploring SHA-256 ASICs as Potential Physical Substrates |
| topic | Neural and Evolutionary Computing C.1.3; I.2.6; B.7.1 |
| url | https://arxiv.org/abs/2601.01916 |