{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T06:27:59Z","timestamp":1786602479668,"version":"build-2736575974"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/icde65706.2026.00274","type":"proceedings-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T19:14:04Z","timestamp":1786562044000},"page":"3694-3707","source":"Crossref","is-referenced-by-count":0,"title":["High-Fidelity and Complex Test Data Generation for Google SQL Code Generation Services"],"prefix":"10.1109","author":[{"given":"Shivasankari","family":"Kannan","sequence":"first","affiliation":[{"name":"Google","place":["Mountain View, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeounoh","family":"Chung","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amita","family":"Gondi","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tristan","family":"Swadell","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fatma","family":"\u00d6zcan","sequence":"additional","affiliation":[{"name":"Google","place":["Mountain View, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1377966.1377977"},{"key":"ref2","article-title":"Market guide for data masking and synthetic data","year":"2024","journal-title":"gartner Market Guide"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113403"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-015-0395-0"},{"key":"ref5","article-title":"Data generation for testing complex queries","author":"Somwase","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3293455"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTW50294.2020.00038"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3649849"},{"key":"ref10","volume-title":"protocolbuffers\/protobuf","year":"25"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3548785.3548793"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.053"},{"key":"ref13","volume-title":"Introduction to sql","year":"2025"},{"key":"ref14","volume-title":"The definitive guide to synthetic data","year":"2024"},{"key":"ref15","volume-title":"Mockaroo: Realistic data generator","year":"2026"},{"key":"ref16","volume-title":"Generate mock data for testing","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347866"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2016.49"},{"key":"ref19","article-title":"Are llms naturally good at synthetic tabular data generation?","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635752"},{"key":"ref21","article-title":"Language models are realistic tabular data generators","author":"Borisov","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Exploring the use of llms for sql equivalence checking","author":"Singh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM59182.2024.00040"},{"key":"ref24","article-title":"Machine learning for synthetic data generation: a review","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SANER60148.2024.00041"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00119"},{"key":"ref27","article-title":"Bare: Combining base and instruction-tuned language models for better synthetic data generation","author":"Zhu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.647"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.208"},{"key":"ref30","article-title":"Mixed-type tabular data synthesis with score-based diffusion in latent space","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"18940","article-title":"Codi: Co-evolving contrastive diffusion models for mixed-type tabular synthesis","volume-title":"International Conference on Machine Learning. PMLR","author":"Lee","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.14778\/3742728.3742761"},{"key":"ref33","article-title":"N12sql is a solved problem\u2026 not!","author":"Floratou","year":"2024","journal-title":"CIDR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574258"},{"key":"ref35","article-title":"Column type annotation using chatgpt","author":"Korini","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Automatic metadata extraction for text-to-sql","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Schema matching with large language models: an experimental study","volume-title":"Proceedings of the 17th International Conference on Web Search and Data Mining (WSDM)","author":"Peeters","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref40","article-title":"Deepjsoneval: Benchmarking complex nested json data mining for large language models","author":"Zhou","year":"2025","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663801"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2023.3334955"},{"key":"ref43","first-page":"104571","article-title":"Efficient medical ner with limited data: Enhancing llm performance through annotation guidelines","volume":"149","author":"Hu","year":"2024","journal-title":"Journal of Biomedical Informatics"},{"key":"ref44","article-title":"Goggle: Generative modelling for tabular data by learning relational structure","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu","year":"2023"},{"issue":"175","key":"ref45","first-page":"1","article-title":"Datawig: Missing value imputation for tables","volume":"20","author":"Biessmann","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3167970"}],"event":{"name":"2026 IEEE 42nd International Conference on Data Engineering (ICDE)","location":"Montreal, QC, Canada","start":{"date-parts":[[2026,5,4]]},"end":{"date-parts":[[2026,5,8]]}},"container-title":["2026 IEEE 42nd International Conference on Data Engineering (ICDE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11629178\/11629165\/11629398.pdf?arnumber=11629398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T05:49:40Z","timestamp":1786600180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11629398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icde65706.2026.00274","relation":{},"subject":[],"published":{"date-parts":[[2026,5]]}}}