SIRIUS-SQL - Anchoring Multi-Candidate Text-to-SQL in Execution Feedback: Risk Stratification and Threshold Selection

Risk stratification is a decision problem in which thresholds, class prevalence, error costs, and downstream actions must be evaluated together. This structured evidence review evaluates "SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback" alongside nine author-disjoint, topically matched publications in enterprise data intelligence. It compares construct definitions, evaluation choices, operating assumptions, and reported limitations instead of treating bibliographic similarity as empirical equivalence. Viewed through risk stratification and threshold selection, the map separates claims supported by the available record from questions that still require full-text extraction, replication, or new experiments. The synthesis is interpretive rather than meta-analytic and therefore does not present a pooled effect estimate or a new causal result. The resulting agenda compares thresholds under observed prevalence, quantifies error costs, and links each stratum to a defined action.

1. Luo, L., Xie, H., Shen, S., Ma, Z., Ling, R., Xu, H., Jiang, H., Chen, D., Li, Y., Chen, P., & Jiang, J. (2026). SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback. arXiv. https://doi.org/10.48550/arXiv.2606.01246 DOI
2. Martin, S. (2011). Annual International Conference on Mobile Communications, Networking and Applications / Business Intelligence & Data Warehouse - Special Track: Data Analysis, Data Quality & Metadata Management. Annual International Conference on Mobile Communications, Networking and Applications / Business Intelligence & Data Warehouse - Special Track: Data Analysis, Data Quality & Metadata Management. https://doi.org/10.5176/978-981-08-9266-1_mobicona-bidw-damd-2011 DOI
3. Gunduz, D., Ergul Azizler, M., & Arslan, E. (2015). Implementation Scenarios of Reporting from Data Warehouse for Business Intelligence. International Journal of Modeling and Optimization, 5(3), 211-215. https://doi.org/10.7763/ijmo.2015.v5.464 DOI
4. Soon, L., & Fraser, C. (2010). Intranet: How is Business Intelligence Stored in a Data Warehouse?. Proceedings of the Annual International Academic Conference on Business Intelligence and Data Warehousing. https://doi.org/10.5176/978-981-08-6308-1_26 DOI
5. Sá, J.-O.-E., & Santos, M.-Y. (2017). Process-driven data analytics supported by a data warehouse model. International Journal of Business Intelligence and Data Mining, 12(4), 383. https://doi.org/10.1504/ijbidm.2017.086986 DOI
6. Aspin, A. (2015). SQL Server Reporting Services as a Business Intelligence Platform. Business Intelligence with SQL Server Reporting Services, 1-17. https://doi.org/10.1007/978-1-4842-0532-7_1 DOI
7. Rudy, R., & Limantara, N. (2011). Model Data Warehouse dan Business Intelligence untuk Meningkatkan Penjualan pada PT. S. ComTech: Computer, Mathematics and Engineering Applications, 2(1), 418. https://doi.org/10.21512/comtech.v2i1.2774 DOI
8. Kurze, C., & Gluchowski, P. (2010). Business Intelligence: Model Driven Architecture für Data Warehouses: Computer Aided Warehouse Engineering - CAWE. Multikonferenz Wirtschaftsinformatik 2010, 217-218. https://doi.org/10.17875/gup2010-1568 DOI
9. Togatorop, P.-R., Sitorus, D., Purba, Y., & Tarigan, A.-M.-F. (2022). Twitter Data Warehouse and Business Intelligence Using Dimensional Model and Data Mining. 2022 IEEE International Conference of Computer Science and Information Technology (ICOSNIKOM), 1-6. https://doi.org/10.1109/icosnikom56551.2022.10034904 DOI
10. Batalla, S. (2024). From data to value: turn unstructured data into a dimensional data model using Data Warehouse (SAP BW/4HANA) and Business Intelligence (SAP Lumira designer) visualizations. Proceedings of the 2024 10th International Conference on Computer Technology Applications, 103-108. https://doi.org/10.1145/3674558.3674572 DOI