Bridging NL2SQL for CAN Signal Analytics at NIO: From Externalized Schemas to CTE Pipelines

Summary: NIO-Weaver enables NL2SQL over CAN warehouses by externalizing DBC-defined, bit-packed signals into a domain graph and hybrid retrieval for ambiguous terms. Hierarchical, self-correcting generation produces executable multi-CTE temporal-analysis pipelines, improving baselines by up to 67.2%. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID: ha20bd6a7cc46641d
Venue: VLDB
Year: 2026
Pagerank: 4.9769913e-05
Overall Rank: 10,949 | 26.41%
DOI: 10.14778/3827998.3828036
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Wei Zhou (Shanghai Jiao Tong University)
2. Haoyu Zhao (Shanghai Jiao Tong University)
3. Ruiguang Zhong (NIO)
4. Shaoli Yu (Shanghai Jiao Tong University)
5. Xuanhe Zhou (Shanghai Jiao Tong University)
6. Xue Yang (Shanghai Jiao Tong University)
7. Xiaosong Jia (Fudan University)
8. Guoliang Li (Tsinghua University)
9. Shengzhong Liu (Shanghai Jiao Tong University)
10. Kang Zhang (China Telecom Corporation Limited)
11. Jie Wu (NIO)
12. Fan Wu (Shanghai Jiao Tong University)

BibTeX Citation

@article{zhou_vldb26,
        title = {{Bridging NL2SQL for CAN Signal Analytics at NIO: From Externalized Schemas to CTE Pipelines}},
        author = {Zhou, Wei and Zhao, Haoyu and Zhong, Ruiguang and Yu, Shaoli and Zhou, Xuanhe and Yang, Xue and Jia, Xiaosong and Li, Guoliang and Liu, Shengzhong and Zhang, Kang and Wu, Jie and Wu, Fan},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {12},
        pages = {4330--4343},
        doi = {10.14778/3827998.3828036},
        url = {https://doi.org/10.14778/3827998.3828036},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,901	Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System	2026	VLDB	4.9769913e-05

Outgoing Citations (Sorted by Pagerank)

Showing 19 of 19 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
31	Hive - A Warehousing Solution Over a Map-Reduce Framework	2009	VLDB	0.00049821554
174	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.00026787121
1,777	OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale	2025	VLDB	9.6599769e-05
2,027	OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment	2025	SIGMOD	9.159284e-05
3,467	In-depth Analysis of Graph-based RAG in a Unified Framework	2025	VLDB	7.2749538e-05
3,489	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB	7.2594757e-05
4,229	Cracking SQL Barriers: An LLM-based Dialect Translation System	2025	SIGMOD	6.7133739e-05
4,346	Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs	2024	VLDB	6.646096e-05
4,925	SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference	2025	SIGMOD	6.3482868e-05
5,546	Automated Validating and Fixing of Text-to-SQL Translation with Execution Consistency	2025	SIGMOD	6.085842e-05
6,107	Breaking It Down: An In-depth Study of Index Advisors	2024	VLDB	5.8833461e-05
8,413	GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications	2025	VLDB	5.3343137e-05
9,226	BenchPress: A Human-in-the-Loop Annotation System for Rapid Text-to-SQL Benchmark Curation	2026	CIDR	5.2032182e-05
9,227	Text-to-SQL Benchmarks are Broken: An In-Depth Analysis of Annotation Errors	2026	CIDR	5.2032182e-05
10,428	Automating Database-Native Function Code Synthesis with LLMs	2026	SIGMOD	4.9769913e-05
10,726	DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs	2026	VLDB	4.9769913e-05
10,901	Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System	2026	VLDB	4.9769913e-05
11,139	OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML	2025	SIGMOD	4.9769913e-05
13,612	DBCooker: A Database Kernel-Specialized Coding Agent Harness	2026	VLDB	-

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	778	Natural language to SQL: Where are we today?	2020	VLDB
2	4,925	SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference	2025	SIGMOD
3	10,901	Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System	2026	VLDB
4	3,489	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB
5	1,356	CatSQL: Towards Real World Natural Language to SQL Applications	2023	VLDB
6	2,349	The Dawn of Natural Language to SQL: Are We Fully Ready?	2024	VLDB
7	10,705	NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions	2026	VLDB
8	9,220	Natural Language to SQL: State of the Art and Open Problems	2025	VLDB
9	2,117	NL2SQL is a solved problem... Not!	2024	CIDR
10	11,474	Welding Natural Language Queries to Analytics IRs with LLMs	2024	CIDR