Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data

arXiv cs.AI Papers
synthetic-data enterprise-data reference-free-evaluation multi-system-synthesis data-generation evaluation-metrics

Summary

The paper introduces a generator that creates consistent fictional enterprise data without real datasets, using reference-free evaluation methods to ensure realism, and includes a hosted service for building relational databases from business questions.

arXiv:2609.11286v1 Announce Type: new Abstract: Synthetic relational data is normally produced by a model trained on a real dataset, and its quality is measured as the distance to that dataset. This paper describes a generator that has no real dataset at either end. Given an industry, a company size, a business model, a set of business applications, and a random seed, it produces a complete fictional enterprise: a workforce, a customer base, sales deals, support tickets, recorded calls, chat messages, and documents, all consistent with one another. One entity graph is projected into the native formats of 66 business products, so the same customer appears in the CRM, the support desk, and the call system under one identity. Because no real counterpart exists, realism is built in from cited reference statistics and verified by reference-free measurement: a five-axis scorecard of 28 statistical checks, an adversarial detector that hunts for the marks of synthetic generation, and a set of soundness checks that include a classifier test against an independently shuffled copy of the data. Because these instruments existed before the generator was tuned, progress is measured under a fixed yardstick: over 23 generated companies, mean realism climbed from 60.3 to 99.1, the weakest company from 41.1 to 94.9, and the detector, which initially flagged 55.2% of all records, now flags none. The scores hold on a seed never used during development. A second generator builds relational databases from a list of business questions. It forces qualifying rows for each answerable question, adds controlled near misses, and computes exact labels from the finished tables. The generator runs as a hosted service at https://console.era.eon.io. A company built there to a specification is served through its simulators over MCP and REST, and the simulators are also published as container images for offline use
Original Article
View Cached Full Text

Cached at: 09/12/26, 08:26 AM 

# Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data
Source: [https://arxiv.org/abs/2609.11286](https://arxiv.org/abs/2609.11286)
[View PDF](https://arxiv.org/pdf/2609.11286)

> Abstract:Synthetic relational data is normally produced by a model trained on a real dataset, and its quality is measured as the distance to that dataset\. This paper describes a generator that has no real dataset at either end\. Given an industry, a company size, a business model, a set of business applications, and a random seed, it produces a complete fictional enterprise: a workforce, a customer base, sales deals, support tickets, recorded calls, chat messages, and documents, all consistent with one another\. One entity graph is projected into the native formats of 66 business products, so the same customer appears in the CRM, the support desk, and the call system under one identity\. Because no real counterpart exists, realism is built in from cited reference statistics and verified by reference\-free measurement: a five\-axis scorecard of 28 statistical checks, an adversarial detector that hunts for the marks of synthetic generation, and a set of soundness checks that include a classifier test against an independently shuffled copy of the data\. Because these instruments existed before the generator was tuned, progress is measured under a fixed yardstick: over 23 generated companies, mean realism climbed from 60\.3 to 99\.1, the weakest company from 41\.1 to 94\.9, and the detector, which initially flagged 55\.2% of all records, now flags none\. The scores hold on a seed never used during development\. A second generator builds relational databases from a list of business questions\. It forces qualifying rows for each answerable question, adds controlled near misses, and computes exact labels from the finished tables\. The generator runs as a hosted service at[this https URL](https://console.era.eon.io/)\. A company built there to a specification is served through its simulators over MCP and REST, and the simulators are also published as container images for offline use

## Submission history

From: Assaf Natanzon \[[view email](https://arxiv.org/show-email/c5c99e23/2609.11286)\] **\[v1\]**Thu, 10 Sep 2026 09:17:21 UTC \(1,024 KB\)

Similar Articles

Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction

arXiv cs.AI

SAP Labs introduces Synthesis Through Simulation (STS), a schema-free data synthesis paradigm where an LLM agent generates enterprise data by executing operations against policy-enforcing APIs in simulated environments, achieving 0.88 average marginal fidelity and 100% constraint satisfaction across ten environments without DB schema access. The full framework and datasets are open-sourced.

Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Data

arXiv cs.LG

The paper proposes GenScript, an inference-only synthetic data pipeline that replaces per-dataset model training by passing a deterministic statistical profile of the source data to an LLM, which infers field semantics and integrity constraints that a coding agent then compiles into an auditable sampler. The approach unifies tabular, temporal, and relational data synthesis, building generators in minutes while closely matching leading methods in fidelity and preserving key integrity constraints.