Verifying Text Summaries of Relational Data Sets
Summary: AggChecker is a natural-language claim verifier for relational data summaries, mapping text claims to SQL translations with probabilistic correctness scores. A holistic model plus efficient candidate pruning, query merging, and result caching enables interactive verification that surfaces inconsistencies and beats baselines. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Saehan Jo (Cornell University)
- 2. Immanuel Trummer (Cornell University)
- 3. Weicheng Yu (Cornell University)
- 4. Xuezhi Wang (Google)
- 5. Cong Yu (Google)
- 6. Daniel Liu (Cornell University)
- 7. Niyati Mehta (Cornell University)
BibTeX Citation
@inproceedings{jo_sigmod19,
title = {{Verifying Text Summaries of Relational Data Sets}},
author = {Jo, Saehan and Trummer, Immanuel and Yu, Weicheng and Wang, Xuezhi and Yu, Cong and Liu, Daniel and Mehta, Niyati},
series = {{SIGMOD} '19},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3299869.3300074},
url = {https://dl.acm.org/doi/10.1145/3299869.3300074},
year = {2019}
}Incoming Citations (Sorted by Pagerank)
Showing 8 of 8 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,356 | CatSQL: Towards Real World Natural Language to SQL Applications | 2023 | VLDB | 0.00010925509 |
| 5,066 | Scrutinizer: Fact Checking Statistical Claims | 2020 | VLDB | 6.2899476e-05 |
| 5,679 | Mining an "Anti-Knowledge Base" from Wikipedia Updates with Applications to Fact Checking and Beyond | 2020 | VLDB | 6.0404239e-05 |
| 7,748 | AggChecker: A Fact-Checking System for Text Summaries of Relational Data Sets | 2019 | VLDB | 5.4600562e-05 |
| 9,579 | On Detecting Cherry-picked Generalizations | 2022 | VLDB | 5.1571823e-05 |
| 11,149 | Demonstrating CEDAR: A System for Cost-Efficient Data-Driven Claim Verification | 2025 | SIGMOD | 4.9793485e-05 |
| 11,364 | CEDAR: A System for Cost-Efficient Data-Driven Claim Verification | 2025 | VLDB | 4.9793485e-05 |
| 11,899 | OREO: Detection of Cherry-picked Generalizations | 2022 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 180 | Constructing an Interactive Natural Language Interface for Relational Databases | 2015 | VLDB | 0.0002654471 |
| 439 | ATHENA: An Ontology-Driven System for Natural Language Querying over Relational Data Stores | 2016 | VLDB | 0.00018251249 |
| 536 | NaLIR: An Interactive Natural Language Interface for Querying Relational Databases | 2014 | SIGMOD | 0.00016771934 |
| 2,482 | ClaimBuster: The First-ever End-to-end Fact-checking System | 2017 | VLDB | 8.399913e-05 |
| 3,178 | Toward Computational Fact-Checking | 2014 | VLDB | 7.5655186e-05 |
| 6,056 | Perturbation Analysis of Database Queries | 2016 | VLDB | 5.9016482e-05 |
| 12,462 | iCheck: Computationally Combating "Lies, D-ned Lies, and Statistics" | 2014 | SIGMOD | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,387 | DBMSs Should Talk Back Too | 2009 | CIDR |
| 2 | 10,804 | Document-to-Database: Extraction Meets Relational Semantics | 2026 | VLDB |
| 3 | 5,544 | Automated Validating and Fixing of Text-to-SQL Translation with Execution Consistency | 2025 | SIGMOD |
| 4 | 11,362 | Finding Convincing Views to Endorse a Claim | 2025 | VLDB |
| 5 | 11,644 | Demonstration of the VeriEQL Equivalence Checker for Complex SQL Queries | 2024 | VLDB |
| 6 | 11,364 | CEDAR: A System for Cost-Efficient Data-Driven Claim Verification | 2025 | VLDB |
| 7 | 10,893 | Developing and Benchmarking Verification Algorithms to Improve Text-to-SQL Generation | 2026 | VLDB |
| 8 | 3,178 | Toward Computational Fact-Checking | 2014 | VLDB |
| 9 | 5,066 | Scrutinizer: Fact Checking Statistical Claims | 2020 | VLDB |
| 10 | 7,748 | AggChecker: A Fact-Checking System for Text Summaries of Relational Data Sets | 2019 | VLDB |