Supplementary Dataset: Serialized System Dynamics Models and Semantic Search Benchmark Logs

This repository contains the supplementary materials and experimental data supporting the research article: "Semantic Search for System Dynamics Models using Vector Embeddings in a Cloud Microservices Environment". The dataset consists of two primary components: 1. Model Corpus (File: system_dynamics_models_corpus.json) This archive contains the source code and serialized JSON structures of 63 System Dynamics models used as the test environment. The models cover diverse domains including economics, biology, epidemiology, and project management. They serve as the "Search Space" for the reported experiments. 2. Experimental Benchmarks (File: benchmark_results_scenario_A.csv) This file contains the raw execution logs for Test Scenario A ("Dynamics of cash flows and resources in economic systems"), comparing the performance of: PostgreSQL Keyword Search (Baseline) Proposed Semantic Search (ONNX/nomic-embed-text-v1.5) Validation of Precision: The benchmark logs verify the reported 100% Precision of the Semantic Search method within the scope of this corpus. The data demonstrates that the semantic vector approach successfully filters out information noise (false positives), whereas the keyword-based approach yielded a 60% noise rate. Note on Semantic Relevance: Models such as "Grain yield and loss model" or "Household Energy Consumption" are classified as Relevant (True Positive) in the logs. This validates the system's ability to detect structural isomorphism—mapping the abstract concept of "economic resource flow" to physically analogous stock-and-flow structures (grain inventory, energy usage), even in the absence of shared terminology.