Cornet: Learning Table Formatting Rules By Example
Summary: Cornet learns spreadsheet conditional-formatting rules from example cells using symbolic rule enumeration ranked by a neural model, introducing inductive synthesis for presentation logic. On 1.8M worksheets (≈450K rules) it outperforms baselines, often yields shorter/hidden rules, and generalizes to filtering and multi-column cases. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Mukul Singh (Microsoft)
- 2. José Cambronero Sánchez (Microsoft)
- 3. Sumit Gulwani (Microsoft)
- 4. Vu Le (Microsoft)
- 5. Carina Negreanu (Microsoft)
- 6. Mohammad Raza (Microsoft)
- 7. Gust Verbruggen (Microsoft)
BibTeX Citation
@article{singh_vldb23,
title = {{Cornet: Learning Table Formatting Rules By Example}},
author = {Singh, Mukul and Sánchez, José Cambronero and Gulwani, Sumit and Le, Vu and Negreanu, Carina and Raza, Mohammad and Verbruggen, Gust},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {10},
pages = {2632--2644},
doi = {10.14778/3603581.3603600},
url = {https://doi.org/10.14778/3603581.3603600},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,692 | FormaT5: Abstention and Examples for Conditional Table Formatting with Natural Language | 2024 | VLDB | 5.3838716e-05 |
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 |
|---|---|---|---|---|
| 1,192 | Query From Examples: An Iterative, Data-Driven Approach to Query Construction | 2015 | VLDB | 0.00011740132 |
| 1,262 | Discovering Queries based on Example Tuples | 2014 | SIGMOD | 0.00011427456 |
| 3,677 | Example-Driven Query Intent Discovery: Abductive Reasoning using Semantic Similarity | 2019 | VLDB | 7.2076465e-05 |
| 6,809 | Web Data Extraction using Hybrid Program Synthesis: A Combination of Top-down and Bottom-up Inference | 2020 | SIGMOD | 5.7663737e-05 |
| 7,749 | CoCo: Interactive Exploration of Conformance Constraints for Data Understanding and Data Cleaning | 2021 | SIGMOD | 5.5525665e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 5,403 | Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples | 2023 | VLDB |
| 2 | 4,412 | Auto-Transform: Learning-to-Transform by Patterns | 2020 | VLDB |
| 3 | 10,390 | AixelNet: A Pre-trained Model with Table-aware Adaptation for Structured Data Prediction | 2026 | SIGMOD |
| 4 | 8,945 | Generation of Training Examples for Tabular Natural Language Inference | 2023 | SIGMOD |
| 5 | 13,337 | Accelerating Tabular Inference: Training Data Generation with TENET | 2025 | VLDB |
| 6 | 7,482 | Table Extraction and Understanding for Scientific and Enterprise Applications | 2020 | VLDB |
| 7 | 3,547 | Learning Semantic String Transformations from Examples | 2012 | VLDB |
| 8 | 8,692 | FormaT5: Abstention and Examples for Conditional Table Formatting with Natural Language | 2024 | VLDB |
| 9 | 8,797 | Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations | 2024 | SIGMOD |
| 10 | 13,398 | Cornet: Learning Spreadsheet Formatting Rules By Example | 2023 | VLDB |