Single-Mind Multi-Body: Core–Body Separation, an Authenticated Task Bus, and Audit-Chain Writeback in a Two-Node Deployment

Abstract. Single-Mind Multi-Body (SMMB) studies the opposite of multi-mind agent clusters: one persistent core plane owns all cross-cycle state and decision authority, while stateless heterogeneous bodies execute atomic tasks. The paper reports a measured two-node instantiation: a core runtime on one host, a stateless body on a second host, an authenticated task bus mounted inside the core, and writeback of every result into a SHA-256 hash-chained audit log. End-to-end latency was 7.22 s median (p90 7.45 s) although execution took 2 ms; an independent probe traced the gap to synchronous whole-file audit-chain writeback, which blocks the core event loop for up to 5.23 s at a 95.9 MB chain. Hash linkage and per-event digests were independently recomputed; body restart re-registered in 91–113 ms; queued work survived body downtime; unauthenticated submissions were rejected. The paper explicitly does not claim multi-body scalability, high availability, energy efficiency, or superiority over multi-agent baselines. Contents. Markdown source, DOCX and PDF; architecture and latency figures; figure-generation script. Experiment scripts and raw outputs are described in the manuscript's data-availability section. Companion artifacts. This record is part of the SMMB long-term program together with P2 (control-theory assumptions, counterexamples and a fair-baseline negative result) and P3 (energy bounding-perspective). Cross-paper claims are limited to each paper's scope; see the claim-boundary table in the manuscript. Status. Working draft; not peer reviewed. Published as a preprint for citation and reproducibility. No venue deadline is implied.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-10-18
DOI
https://doi.org/10.5281/zenodo.23447713
Citations
2
Primary Topic
Distributed systems and fault tolerance
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

Single-Mind Multi-Body: Core–Body Separation, an Authenticated Task Bus, and Audit-Chain Writeback in a Two-Node Deployment

Miaosheng Wang
2 citations
Zenodo (CERN European Organization for Nuclear Research)
Distributed systems and fault tolerance
preprint

Single-Mind Multi-Body: Core–Body Separation, an Authenticated Task Bus, and Audit-Chain Writeback in a Two-Node Deployment

Miaosheng Wang
preprint en
2 citations

Abstract

Abstract. Single-Mind Multi-Body (SMMB) studies the opposite of multi-mind agent clusters: one persistent core plane owns all cross-cycle state and decision authority, while stateless heterogeneous bodies execute atomic tasks. The paper reports a measured two-node instantiation: a core runtime on one host, a stateless body on a second host, an authenticated task bus mounted inside the core, and writeback of every result into a SHA-256 hash-chained audit log. End-to-end latency was 7.22 s median (p90 7.45 s) although execution took 2 ms; an independent probe traced the gap to synchronous whole-file audit-chain writeback, which blocks the core event loop for up to 5.23 s at a 95.9 MB chain. Hash linkage and per-event digests were independently recomputed; body restart re-registered in 91–113 ms; queued work survived body downtime; unauthenticated submissions were rejected. The paper explicitly does not claim multi-body scalability, high availability, energy efficiency, or superiority over multi-agent baselines. Contents. Markdown source, DOCX and PDF; architecture and latency figures; figure-generation script. Experiment scripts and raw outputs are described in the manuscript's data-availability section. Companion artifacts. This record is part of the SMMB long-term program together with P2 (control-theory assumptions, counterexamples and a fair-baseline negative result) and P3 (energy bounding-perspective). Cross-paper claims are limited to each paper's scope; see the claim-boundary table in the manuscript. Status. Working draft; not peer reviewed. Published as a preprint for citation and reproducibility. No venue deadline is implied.

Zenodo (CERN European Organization for Nuclear Research)
Distributed systems and fault tolerance
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.