CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics

Export BriefConnect with Author
View PDF ↗
PDF Viewer
Open Full PDF

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

Estimated $10K - $14K over 6-10 weeks.

See exactly what it costs to build this -- with 3 comparable funded startups.

7-day free trial. Cancel anytime.

Discover the researchers behind this paper and find similar experts.

7-day free trial. Cancel anytime.

References (65)

[1]
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
2025Yanzhao Zhang, Mingxin Li et al.
[2]
multivariateGPT: a decoder-only transformer for multivariate categorical and numeric data
2025Andrew Loza, Jun Yup Kim et al.
[3]
Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting
2025Gyanendra Shrestha, Chutian Jiang et al.
[4]
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
2025Xinshuo Hu, Zifei Shan et al.
[5]
Jasper and Stella: distillation of SOTA embedding models
2024Dun Zhang, Jiacheng Li et al.
[6]
Magneto: Combining Small and Large Language Models for Schema Matching
2024Yurong Liu, Eduardo Peña et al.
[7]
Interleaving Text and Number Embeddings to Solve Mathemathics Problems
2024Marvin Alberts, Gianmarco Gabrieli et al.
[8]
How to Leverage Digit Embeddings to Represent Numbers?
2024Jasivan Sivakumar, N. Moosavi
[9]
In Situ Neural Relational Schema Matcher
2024Xingyu Du, Gongsheng Yuan et al.
[10]
NumeroLogic: Number Encoding for Enhanced LLMs’ Numerical Reasoning
2024Eli Schwartz, Leshem Choshen et al.
[11]
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
2024Jianlv Chen, Shitao Xiao et al.
[12]
Dominance of AI and Machine Learning Techniques in Hybrid Movie Recommendation System Applying Text-to-number Conversion and Cosine Similarity Approaches
2024Md Rokibul Hasan, Janatul Ferdous MSc
[13]
Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings
2022Danushka Bollegala
[14]
On Embeddings for Numerical Features in Tabular Deep Learning
2022Yura Gorishniy, Ivan Rubachev et al.
[15]
Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question Answering
2022Jeonghwan Kim, Junmo Kang et al.
[16]
Predicting Numerals in Natural Language Text Using a Language Model Considering the Quantitative Aspects of Numerals
2021Taku Sakamoto, Akiko Aizawa
[17]
TABBIE: Pretrained Representations of Tabular Data
2021H. Iida, Dung Ngoc Thai et al.
[18]
Numeracy enhances the Literacy of Language Models
2021Avijit Thawani, J. Pujara et al.
[19]
Methods for Numeracy-Preserving Word Embeddings
2020Dhanasekar Sundararaman, Shijing Si et al.
[20]
An Empirical Investigation of Contextualized Number Prediction
2020Daniel M. Spokoyny, Taylor Berg-Kirkpatrick

Showing 20 of 65 references

Founder's Pitch

"Develop CONE, a hybrid transformer model that improves numerical reasoning in large-scale datasets for various domains by embedding numbers with semantics."

LLM TrainingScore: 8View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

2/4 signals

5

Quick Build

3/4 signals

7.5

Series A Potential

3/4 signals

7.5

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 3/5/2026

Explore the full citation network and related research.

7-day free trial. Cancel anytime.

Understand the commercial significance and market impact.

7-day free trial. Cancel anytime.

Get detailed profiles of the research team.

7-day free trial. Cancel anytime.

Related Papers

Loading…