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 This section contains the raw execution logs for five distinct test scenarios (A–E). These files document the comparative analysis between the PostgreSQL Keyword Search (Baseline) and the Proposed Semantic Search (ONNX/nomic-embed-text-v1.5). Scenario A: Dynamics of cash flows and resources (File: benchmark_results_scenario_A.csv) Focus: Validation of Precision. Key Finding: Verifies the reported 100% Precision of the Semantic Search method. The data demonstrates effective filtering of information noise (false positives), whereas the keyword-based approach yielded a 60% noise rate. It highlights the system's ability to detect structural isomorphism (e.g., mapping "economic resource flow" to "grain inventory"). Scenario B: Rosenzweig-MacArthur model stability (File: benchmark_results_scenario_B.csv) Focus: Zero-Shot Retrieval & Recall. Key Finding: Illustrates a case where the keyword baseline failed completely (0 results) due to missing exact terminology. The Semantic Search method successfully retrieved the target "Rosenzweig-MacArthur Predator-Prey Model" (Rank 1) by mapping the abstract concept of "stability" to the model's cyclic dynamics. Scenario C: Climate influence on viral transmission (File: benchmark_results_scenario_C.csv) Focus: Contextual Filtering. Key Finding: Highlights noise reduction (90% Precision vs 16% Baseline). The semantic approach successfully prioritized "viral transmission" contexts (pathogens, antibodies) while filtering out irrelevant ecological models that simply contained the generic word "influence". Scenario D: Weighted gene regulatory network modeling (File: benchmark_results_scenario_D.csv) Focus: Semantic Disambiguation. Key Finding: Demonstrates robustness against substring matching errors. While the baseline suffered from 75% false positives (matching "gene" within "Generation" in power grid models), the semantic search maintained 100% precision, correctly distinguishing biological gene regulation from linguistic noise in energy and waste management domains. Scenario E: Population dynamics with seasonal migration patterns (File: benchmark_results_scenario_E.csv) Focus: Conceptual Mapping of Complex Dynamics. Key Finding: Verifies the ability to retrieve models based on behavioral descriptions. The semantic engine successfully retrieved models exhibiting "seasonal migration" and "climatic influence" (100% Precision), linking the query to structurally analogous stock-and-flow dynamics even when explicit "migration" terminology was variable or absent.