{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:37:02Z","timestamp":1772933822142,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11400858","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"7173-7180","source":"Crossref","is-referenced-by-count":0,"title":["SQuARE: Structured Query & Adaptive Retrieval Engine for Tabular Formats"],"prefix":"10.1109","author":[{"given":"Chinmay","family":"Gondhalekar","sequence":"first","affiliation":[{"name":"Ratings Data Science, S&P Global,New York,United States of America"}]},{"given":"Urjitkumar","family":"Patel","sequence":"additional","affiliation":[{"name":"Ratings Data Science, S&P Global,New York,United States of America"}]},{"given":"Fang-Chun","family":"Yeh","sequence":"additional","affiliation":[{"name":"Ratings Data Science, S&P Global,New York,United States of America"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Hello GPT-4o","year":"2024"},{"key":"ref2","volume-title":"Tabrag: Efficient table retrieval and understanding with large multimodal models","author":"Xu","year":"2024"},{"key":"ref3","volume-title":"Tablerag: A retrieval-augmented generation framework for heterogeneous document reasoning","author":"Yu","year":"2025"},{"key":"ref4","article-title":"Tablerag extended: Mixed retrieval and sql reasoning for tabular qa","volume-title":"OpenReview","author":"Yu","year":"2025"},{"key":"ref5","volume-title":"Fine-tuning embedding models for tabular retrieval-augmented generation in financial datasets","author":"Khanna","year":"2024"},{"key":"ref6","author":"Report","year":"2023","journal-title":"Structured retrieval-augmented generation for tables"},{"key":"ref7","volume-title":"Agentic nl2sql to reduce computational costs","author":"Jehle","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIC60265.2024.10433839"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825891"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"ref11","first-page":"4320","article-title":"Tapas: Weakly supervised table parsing via pretraining","author":"Herzig","year":"2020","journal-title":"EMNLP"},{"key":"ref12","author":"Zhang","year":"2021","journal-title":"Tabbie: Pretraining for table representation learning"},{"key":"ref13","article-title":"Tabpfn: Approximating bayesian neural networks with transformers for tabular data","author":"Hollmann","year":"2025","journal-title":"Nature Machine Intelligence"},{"key":"ref14","author":"Hollmann","year":"2025","journal-title":"Tabpfnv2: Scaling tabpfn for large tabular datasets"},{"key":"ref15","article-title":"Tabicl: Scaling tabular foundation models with incontext learning","author":"Qu","year":"2025","journal-title":"ICML"},{"key":"ref16","author":"Ma","year":"2024","journal-title":"Tabdpt: Retrieval-pretrained tabular transformer for zero-shot and few-shot learning"},{"key":"ref17","article-title":"Why tabular foundation models should be the focus of ai research","volume-title":"ICML Workshop on Foundation Models","author":"Van Breugel","year":"2024"},{"key":"ref18","volume-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2020"},{"key":"ref19","author":"Team","year":"2024","journal-title":"Gemma: Open models based on gemini research and technology"},{"key":"ref20","year":"2024","journal-title":"Introducing llama 3.1: Our most capable models to date"},{"key":"ref21","volume-title":"Google colaboratory","year":"2023"},{"key":"ref22","volume-title":"Gpu schedules architecture notebook","author":"Zhang","year":"2023"},{"key":"ref23","author":"Gondhalekar","year":"2025","journal-title":"Multifinrag: An optimized multimodal retrieval-augmented generation (rag) framework for financial question answering"},{"key":"ref24","year":"2025","journal-title":"Introducing gpt-5"},{"key":"ref25","article-title":"Introducing gpt-oss","year":"2025","journal-title":"open-weight 20B\/120 B announcement"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-024-40763-6","volume-title":"Large language models for table processing: A survey","author":"Lu","year":"2025"},{"key":"ref27","volume-title":"Table models are few-shot learners? xtformer for cross-table learning","author":"Zhang","year":"2024"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11400858.pdf?arnumber=11400858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:52:45Z","timestamp":1772866365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11400858\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11400858","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}