# Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models

arXiv: https://arxiv.org/abs/2607.21636 · HTML: https://mlsanity.com/paper/2607.21636/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 55 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [A Continuous Time Framework for Discrete Denoising Models](https://mlsanity.com/paper/2205.14987/) (2022)
- [Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data](https://mlsanity.com/paper/2406.03736/) (2024)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Revisiting Classifier Two-Sample Tests](https://mlsanity.com/paper/1610.06545/) (2016)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [STaSy: Score-based Tabular data Synthesis](https://mlsanity.com/paper/2210.04018/) (2022)
- [Variational Flow Matching for Graph Generation](https://mlsanity.com/paper/2406.04843/) (2024)
- [CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis](https://mlsanity.com/paper/2304.12654/) (2023)
- [TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation](https://mlsanity.com/paper/2410.20626/) (2024)
- [Classification accuracy as a proxy for two sample testing](https://mlsanity.com/paper/1602.02210/) (2016)
- [Exponential Family Variational Flow Matching for Tabular Data Generation](https://mlsanity.com/paper/2506.05940/) (2025)
- [LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion](https://mlsanity.com/paper/2503.02161/) (2025)
- [Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class](https://mlsanity.com/paper/2412.15657/) (2024)
- [Structured Evaluation of Synthetic Tabular Data](https://mlsanity.com/paper/2403.10424/) (2024)
- [Benchmarking the Fidelity and Utility of Synthetic Relational Data](https://mlsanity.com/paper/2410.03411/) (2024)
- [Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies](https://mlsanity.com/paper/2509.19707/) (2025)
- [Flow Matching for Tabular Data Synthesis](https://mlsanity.com/paper/2512.00698/) (2025)
- [Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features](https://mlsanity.com/paper/2601.22816/) (2026)
- [Assessing Generative Models for Structured Data](https://mlsanity.com/paper/2503.20903/) (2025)
- [Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference](https://mlsanity.com/paper/2602.13813/) (2026)

## Built on by (most cited first, 2 of 2)

- [The Era by Eon Benchmark: A Generated Enterprise Estate with Exact Ground Truth for Benchmarking LLM Agents](https://mlsanity.com/paper/2609.09853/) (2026)
- [Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data](https://mlsanity.com/paper/2609.11286/) (2026)

## Abstract (arXiv)

Synthetic tabular data are valued for preserving inter-column dependency, yet each routine fidelity score is a single number that says neither where that dependency is lost nor why. We localize the deficit inside a single score. Equipping a classifier two-sample test (C2ST) with a gradient-boosted discriminator, we decompose it by controlled permutation into marginal, dependency, and numerical-categorical cross components, each read against a fully factorized reference that destroys all dependency while leaving every marginal intact, and against a real-data oracle. The linear detection score in common use rates that same reference as nearly real, a known weakness we replicate on four benchmarks. Applied to a flow-matching (TabbyFlow) and a diffusion (TabDiff) generator, the decomposition exposes a dependency deficit of the same order in both, and we then narrow its source by elimination: it is not a structural limit of the mean-field objective, it is not sampling discretization, and a 16x capacity increase does not close it, while the same measurement responds sharply when capacity is instead cut eightfold, so the plateau is measured rather than a blind spot. Destroying dependency outright collapses minority-class F1 by 0.38-0.61, which bounds what is at stake, though the generators' much smaller residual deficits do not predict their remaining shortfalls. What survives points at the objective: nothing in it scores the joint. Cheap remedies are no substitute: an explicit cross-coupling module and a post-hoc copula both leave the deficit in place.