<![CDATA[Purpose – This study evaluates when dependency-aware parallel scheduling improves a single-node simulated smart-contract workload for organic certification while separating scheduling effects from hash-chain and dependency-graph record representation.Methods – A deterministic Python rule engine evaluates 18 certification tasks per submission. The same transactions were executed under four conditions: hash-chain sequential (HS), hash-chain dependency-aware parallel (HP), dependency-graph sequential (DS), and dependency-graph dependency-aware parallel (DP). Main experiments varied 18–900 transactions and 1–3,000 iterative SHA-256 rounds, with five warm-ups and 30 paired technical repetitions. Worker, graph-shape, conflict, functional, integrity, and focused reconciliation tests were also performed.Findings – Representation-only ratios remained close to unity, whereas scheduling produced the dominant performance effect. At 3,000 rounds, HP/HS and DP/DS speedups were 1.680× and 1.620× at 450 transactions and 1.564× and 1.554× at 900 transactions. The focused reconciliation run showed that eight workers minimized makespan for both 180 and 900 transactions, although per-worker efficiency declined as worker count increased. All 12 functional and integrity tests passed.Research Implications – Dependency information is useful primarily as a scheduling mechanism; the observed speedup should not be interpreted as evidence that a distributed DAG ledger is intrinsically faster than a hash chain.Originality – The study provides a carefully documented 2 × 2 single-node benchmark that isolates record representation from execution policy for a simulated certification smart-contract workload.]]>
Copyrights © 2026
