CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics
Summary: CONE is a hybrid transformer embedding model for numbers, ranges, and Gaussians that jointly encodes values with units and attribute names while preserving numerical distance. Across web, medical, finance, and government data, it substantially improves numerical reasoning and retrieval over SOTA. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Gyanendra Shrestha (Florida State University)
- 2. Anna Pyayt (University of South Florida)
- 3. Michael Gubanov (Florida State University)
BibTeX Citation
@inproceedings{shrestha_sigmod26,
title = {{CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics}},
author = {Shrestha, Gyanendra and Pyayt, Anna and Gubanov, Michael},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802049},
url = {https://dl.acm.org/doi/10.1145/3802049},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 183 | Applying Model Management to Classical Meta Data Problems | 2003 | CIDR | 0.00026283359 |
| 397 | TURL: Table Understanding through Representation Learning | 2021 | VLDB | 0.00019278189 |
| 762 | Model Management 2.0: Manipulating Richer Mappings | 2007 | SIGMOD | 0.00014231163 |
| 1,723 | Rondo: A Programming Platform for Generic Model Management | 2003 | SIGMOD | 9.9204974e-05 |
| 5,293 | Magneto: Combining Small and Large Language Models for Schema Matching | 2025 | VLDB | 6.279939e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,248 | Generalized Entity Matching with Adaptivity via Large Language Models | 2026 | SIGMOD |
| 2 | 3,092 | DeepSqueeze: Deep Semantic Compression for Tabular Data | 2020 | SIGMOD |
| 3 | 489 | Distributed Representations of Tuples for Entity Resolution | 2018 | VLDB |
| 4 | 10,381 | Integrating Vector Databases across Embedding Models | 2026 | SIGMOD |
| 5 | 6,192 | Pre-trained Embeddings for Entity Resolution: An Experimental Analysis | 2023 | VLDB |
| 6 | 10,206 | Bridging the Gap: Cardinality Estimation for Semantic Queries on Unstructured Data | 2026 | SIGMOD |
| 7 | 10,203 | BEACON: Budget-Aware Entity Matching Across Domains | 2026 | SIGMOD |
| 8 | 6,115 | Fine-grained Concept Linking using Neural Networks in Healthcare | 2018 | SIGMOD |
| 9 | 1,402 | Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks | 2020 | SIGMOD |
| 10 | 6,341 | Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks | 2024 | SIGMOD |