Alexandra Brintrup, Ge Zheng, Liming Xu, Yunbo Long
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Synthetic data offers a promising solution to two persistent barriers in supply chain analytics: data scarcity and data privacy. However, for synthetic data to support operational simulation and decision-making, it must do more than reproduce the statistical distributions of real records, and also preserve the operational logic that governs supply chain processes, including the temporal orderings, mathematical dependencies, hierarchical taxonomies, and conditional rules that make a record operationally plausible. We consider this logic as the "physics" of supply chain data. Existing tabular generative models are primarily optimized for distributional fidelity and downstream predictive utility, and therefore often generate records that appear statistically realistic but violate fundamental operational constraints. This paper introduces TabKG, a knowledge-graph-guided framework for logically consistent synthetic supply chain tabular data generation. TabKG constructs a Column Relationship Knowledge Graph (CR-KG) to represent data operational dependencies. It uses a multi-LLM ensemble with majority voting to propose candidate relationships from column metadata, validates these relationships against real data to remove hallucinated or unsupported edges, and then uses the validated CR-KG to guide generation. Specifically, TabKG compresses the original table into independent columns, generates these columns using a latent diffusion model, and deterministically reconstructs dependent columns according to the validated relationships, enforcing logical consistency by construction with respect to the discovered operational rules. Across two industrial supply chain datasets and two downstream classification tasks, namely late-delivery risk prediction and procurement-status classification, TabKG achieves an F1 score of up to 0.97 for operational logic reasoning. This is substantially higher than prompt-only baselines, whose F1 scores range from 0.27 to 0.55. For tabular data generation, TabKG performs comparably to four state-of-the-art tabular generative baselines in terms of fidelity, utility, and privacy, while achieving stronger logical consistency. These results show that trustworthy synthetic supply chain data should preserve not only statistical realism, but also the operational rules that govern the real system. Overall, TabKG provides a foundation for moving synthetic data beyond machine learning augmentation toward high-fidelity supply chain simulation and operational decision support. The code is available at https://github.com/Yunbomax/TabKG.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2605.26823")
get_code_for_paper("2605.26823")
have("2605.26823")
Connect an agent — have() is free.